Supercluster Network of Graphical Processing Units (gpus)

(1) U.S. Provisional Application No. 63/422,650, filed on Nov. 4, 2022; (2) U.S. Provisional Application No. 63/424,282, filed on Nov. 10, 2022; (3) U.S. Provisional Application No. 63/425,646, filed on Nov. 15, 2022; (4) U.S. Provisional Application No. 63/460,766, filed on Apr. 20, 2023; (5) U.S. Provisional Application No. 63/583,512, filed on Sep. 18, 2023; The present application is a continuation of Non-provisional patent application Ser. No. 18/500,463 filed Nov. 2, 2023, and claims the benefit of each of the following provisional applications. The entire contents of each of the following provisional applications is incorporated herein by reference for all purposes:

The present disclosure generally relates to cloud architectures, and more particularly to a supercluster architecture of graphical processing units (GPUs). More specifically, the present disclosure is related to a network architecture that provides for hybrid clusters of GPUs (e.g., different generations of GPUs, or GPUs operating at different speeds, etc.) to coexist in a same network fabric. The supercluster architecture provides for seamless scaling of GPUs with the ever increasing customer demands.

Organizations continue to move business applications and databases to the cloud to reduce the cost of purchasing, updating, and maintaining on premise hardware and software. High performance computer applications consistently consume all of the available compute power to achieve a specific outcome or result. Such applications require dedicated network performance, fast storage, high compute capabilities, and significant amounts of memory-resources that are in short supply in the virtualized infrastructure that constitutes today's commodity clouds.

Cloud infrastructure service providers offer newer and faster graphical processing units (GPUs) to address the requirements of such applications. A GPU workload is typically executed on one or more host machines. Typically, such workloads are not able to achieve an expected level of throughput. One factor for this problem is the lack of flow entropy e.g., equal cost multi-path (ECMP) flow entropy. Furthermore, the problem is worsened by the fact that host machines (i.e., hosts) exchange traffic without regard for which other hosts are in their local network neighborhood.

4 Moreover, traditional GPU clusters generally scale in the range of 1K toK GPUs. The limit on scaling the number of GPUs is due a limitation imposed by a network topology that is constructed to support the GPU clusters. The network topology constructed to support GPU clusters incurs a significant amount of oversubscription, thus posing challenges to scale the cluster. Further, the traditional GPU clusters impose strict limitations on the routing policy employed within the cluster. For instance, traditional GPU clusters do not support standard custom routing protocols. Additionally, the traditional GPU clusters are built in a manner such that they support one transmission speed for all GPUs in the cluster. Thus, there is a requirement to build a GPU cluster that can scale at levels much higher than those of traditional GPUs clusters as well support communication between different GPU clusters operating at different transmission speeds. Embodiments discussed herein address these and other issues.

The present disclosure relates to cloud architectures, and more particularly to a supercluster architecture of graphical processing units (GPUs). More specifically, the present disclosure is related to a network architecture that provides for hybrid clusters of GPUs (e.g., different generations of GPUs, or GPUs operating at different speeds, etc.) to coexist in a same network fabric. The supercluster architecture provides for seamless scaling of GPUs with the ever increasing customer demands. Various embodiments are described herein, including methods, systems, non-transitory computer-readable storage media storing programs, code, or instructions executable by one or more processors, and the like. Some embodiments may be implemented by using a computer program product, comprising computer program/instructions which, when executed by a processor, cause the processor to perform any of the methods described in the disclosure.

One aspect of the present disclosure provides for a method comprising: providing a network fabric including: (i) a plurality of graphical processing unit (GPU) clusters, the plurality of GPU clusters including at least a first GPU cluster operating at a first speed and a second GPU cluster operating at a second speed that is different than the first speed, and (ii) a plurality of blocks, wherein each block includes: (a) one or more racks that host a GPU cluster, and (b) a plurality of switches arranged in a hierarchical structure that communicatively couple the block to other blocks included in the network fabric; and responsive to receiving a request to execute a workload, allocating one or more GPUs from the plurality of GPU clusters to execute the workload.

An aspect of the present disclosure provides for a computing device comprising one or more data processors, and a non-transitory computer readable storage medium containing instructions which, when executed on the one or more data processors, cause the computing device to perform part or all of one or more methods disclosed herein.

Another aspect of the present disclosure provides for a computer-program product tangibly embodied in a non-transitory machine-readable storage medium, including instructions configured to cause one or more data processors to perform part or all of one or more methods disclosed herein.

The foregoing, together with other features and embodiments will become more apparent upon referring to the following specification, claims, and accompanying drawings.

In the following description, for the purposes of explanation, specific details are set forth in order to provide a thorough understanding of certain embodiments. However, it will be apparent that various embodiments may be practiced without these specific details. The figures and description are not intended to be restrictive. The word “exemplary” is used herein to mean “serving as an example, instance, or illustration.” Any embodiment or design described herein as “exemplary” is not necessarily to be construed as preferred or advantageous over other embodiments or designs.

Embodiments of the present disclosure relate to cloud architectures, and more particularly to a supercluster architecture of graphical processing units (GPUs). More specifically, the present disclosure is related to a network architecture that provides for hybrid clusters of GPUs (e.g., different generations of GPUs, or GPUs operating at different speeds, etc.) to coexist in a same network fabric. The supercluster architecture provides for seamless scaling of GPUs with the ever increasing customer demands.

The term cloud service is generally used to refer to a service that is made available by a cloud services provider (CSP) to users or customers on demand (e.g., via a subscription model) using systems and infrastructure (cloud infrastructure) provided by the CSP. Typically, the servers and systems that make up the CSP's infrastructure are separate from the customer's own on-premises servers and systems. Customers can thus avail themselves of cloud services provided by the CSP without having to purchase separate hardware and software resources for the services. Cloud services are designed to provide a subscribing customer easy, scalable access to applications and computing resources without the customer having to invest in procuring the infrastructure that is used for providing the services.

There are several cloud service providers that offer various types of cloud services. There are various different types or models of cloud services including Software-as-a-Service (SaaS), Platform-as-a-Service (PaaS), Infrastructure-as-a-Service (IaaS), and others.

A customer can subscribe to one or more cloud services provided by a CSP. The customer can be any entity such as an individual, an organization, an enterprise, and the like. When a customer subscribes to or registers for a service provided by a CSP, a tenancy or an account is created for that customer. The customer can then, via this account, access the subscribed-to one or more cloud resources associated with the account.

As noted above, infrastructure as a service (IaaS) is one particular type of cloud computing service. In an IaaS model, the CSP provides infrastructure (referred to as cloud services provider infrastructure or CSPI) that can be used by customers to build their own customizable networks and deploy customer resources. The customer's resources and networks are thus hosted in a distributed environment by infrastructure provided by a CSP. This is different from traditional computing, where the customer's resources and networks are hosted by infrastructure provided by the customer.

The CSPI may comprise interconnected high-performance compute resources including various host machines, memory resources, and network resources that form a physical network, which is also referred to as a substrate network or an underlay network. The resources in CSPI may be spread across one or more data centers that may be geographically spread across one or more geographical regions. Virtualization software may be executed by these physical resources to provide a virtualized distributed environment. The virtualization creates an overlay network (also known as a software-based network, a software-defined network, or a virtual network) over the physical network. The CSPI physical network provides the underlying basis for creating one or more overlay or virtual networks on top of the physical network. The physical network (or substrate network or underlay network) comprises physical network devices such as physical switches, routers, computers and host machines, and the like. An overlay network is a logical (or virtual) network that runs on top of a physical substrate network. A given physical network can support one or multiple overlay networks. Overlay networks typically use encapsulation techniques to differentiate between traffic belonging to different overlay networks. A virtual or overlay network is also referred to as a virtual cloud network (VCN). The virtual networks are implemented using software virtualization technologies (e.g., hypervisors, virtualization functions implemented by network virtualization devices (NVDs) (e.g., smartNICs), top-of-rack (TOR) switches, smart TORs that implement one or more functions performed by an NVD, and other mechanisms) to create layers of network abstraction that can be run on top of the physical network. Virtual networks can take on many forms, including peer-to-peer networks, IP networks, and others. Virtual networks are typically either Layer-3 IP networks or Layer-2 VLANs. This method of virtual or overlay networking is often referred to as virtual or overlay Layer-3 networking. Examples of protocols developed for virtual networks include IP-in-IP (or Generic Routing Encapsulation (GRE)) Virtual Extensible LAN (VXLAN-IETF RFC 7348), Virtual Private Networks (VPNs) (e.g., MPLS Layer-3 Virtual Private Networks (RFC 4364)), VMware's NSX, GENEVE (Generic Network Virtualization Encapsulation), and others.

For IaaS, the infrastructure (CSPI) provided by a CSP can be configured to provide virtualized computing resources over a public network (e.g., the Internet). In an IaaS model, a cloud computing services provider can host the infrastructure components (e.g., servers, storage devices, network nodes (e.g., hardware), deployment software, platform virtualization (e.g., a hypervisor layer), or the like). In some cases, an IaaS provider may also supply a variety of services to accompany those infrastructure components (e.g., billing, monitoring, logging, security, load balancing and clustering, etc.). Thus, as these services may be policy-driven, IaaS users may be able to implement policies to drive load balancing to maintain application availability and performance. CSPI provides infrastructure and a set of complementary cloud services that enable customers to build and run a wide range of applications and services in a highly available hosted distributed environment. CSPI offers high-performance compute resources and capabilities and storage capacity in a flexible virtual network that is securely accessible from various networked locations such as from a customer's on-premises network. When a customer subscribes to or registers for an IaaS service provided by a CSP, the tenancy created for that customer is a secure and isolated partition within the CSPI where the customer can create, organize, and administer their cloud resources.

Customers can build their own virtual networks using compute, memory, and networking resources provided by CSPI. One or more customer resources or workloads, such as compute instances, can be deployed on these virtual networks. For example, a customer can use resources provided by CSPI to build one or multiple customizable and private virtual network(s) referred to as virtual cloud networks (VCNs). A customer can deploy one or more customer resources, such as compute instances, on a customer VCN. Compute instances can take the form of virtual machines, bare metal instances, and the like. The CSPI thus provides infrastructure and a set of complementary cloud services that enable customers to build and run a wide range of applications and services in a highly available virtual hosted environment. The customer does not manage or control the underlying physical resources provided by CSPI but has control over operating systems, storage, and deployed applications; and possibly limited control of select networking components (e.g., firewalls).

The CSP may provide a console that enables customers and network administrators to configure, access, and manage resources deployed in the cloud using CSPI resources. In certain embodiments, the console provides a web-based user interface that can be used to access and manage CSPI. In some implementations, the console is a web-based application provided by the CSP.

CSPI may support single-tenancy or multi-tenancy architectures. In a single tenancy architecture, a software (e.g., an application, a database) or a hardware component (e.g., a host machine or a server) serves a single customer or tenant. In a multi-tenancy architecture, a software or a hardware component serves multiple customers or tenants. Thus, in a multi-tenancy architecture, CSPI resources are shared between multiple customers or tenants. In a multi-tenancy situation, precautions are taken, and safeguards put in place within CSPI to ensure that each tenant's data is isolated and remains invisible to other tenants.

In a physical network, a network endpoint (“endpoint”) refers to a computing device or system that is connected to a physical network and communicates back and forth with the network to which it is connected. A network endpoint in the physical network may be connected to a Local Area Network (LAN), a Wide Area Network (WAN), or other type of physical network. Examples of traditional endpoints in a physical network include modems, hubs, bridges, switches, routers, and other networking devices, physical computers (or host machines), and the like. Each physical device in the physical network has a fixed network address that can be used to communicate with the device. This fixed network address can be a Layer-2 address (e.g., a MAC address), a fixed Layer-3 address (e.g., an IP address), and the like. In a virtualized environment or in a virtual network, the endpoints can include various virtual endpoints such as virtual machines that are hosted by components of the physical network (e.g., hosted by physical host machines). These endpoints in the virtual network are addressed by overlay addresses such as overlay Layer-2 addresses (e.g., overlay MAC addresses) and overlay Layer-3 addresses (e.g., overlay IP addresses). Network overlays enable flexibility by allowing network managers to move around the overlay addresses associated with network endpoints using software management (e.g., via software implementing a control plane for the virtual network). Accordingly, unlike in a physical network, in a virtual network, an overlay address (e.g., an overlay IP address) can be moved from one endpoint to another using network management software. Since the virtual network is built on top of a physical network, communications between components in the virtual network involves both the virtual network and the underlying physical network. In order to facilitate such communications, the components of CSPI are configured to learn and store mappings that map overlay addresses in the virtual network to actual physical addresses in the substrate network, and vice versa. These mappings are then used to facilitate the communications. Customer traffic is encapsulated to facilitate routing in the virtual network.

Accordingly, physical addresses (e.g., physical IP addresses) are associated with components in physical networks and overlay addresses (e.g., overlay IP addresses) are associated with entities in virtual or overlay networks. A physical IP address is an IP address associated with a physical device (e.g., a network device) in the substrate or physical network. For example, each NVD has an associated physical IP address. An overlay IP address is an overlay address associated with an entity in an overlay network, such as with a compute instance in a customer's virtual cloud network (VCN). Two different customers or tenants, each with their own private VCNs can potentially use the same overlay IP address in their VCNs without any knowledge of each other. Both the physical IP addresses and overlay IP addresses are types of real IP addresses. These are separate from virtual IP addresses. A virtual IP address is typically a single IP address that is represents or maps to multiple real IP addresses. A virtual IP address provides a 1-to-many mapping between the virtual IP address and multiple real IP addresses. For example, a load balancer may use a VIP to map to or represent multiple servers, each server having its own real IP address.

The cloud infrastructure or CSPI is physically hosted in one or more data centers in one or more regions around the world. The CSPI may include components in the physical or substrate network and virtualized components (e.g., virtual networks, compute instances, virtual machines, etc.) that are in a virtual network built on top of the physical network components. In certain embodiments, the CSPI is organized and hosted in realms, regions, and availability domains. A region is typically a localized geographic area that contains one or more data centers. Regions are generally independent of each other and can be separated by vast distances, for example, across countries or even continents. For example, a first region may be in Australia, another one in Japan, yet another one in India, and the like. CSPI resources are divided among regions such that each region has its own independent subset of CSPI resources. Each region may provide a set of core infrastructure services and resources, such as, compute resources (e.g., bare metal servers, virtual machine, containers and related infrastructure, etc.); storage resources (e.g., block volume storage, file storage, object storage, archive storage); networking resources (e.g., virtual cloud networks (VCNs), load balancing resources, connections to on-premise networks), database resources; edge networking resources (e.g., DNS); and access management and monitoring resources, and others. Each region generally has multiple paths connecting it to other regions in the realm.

Generally, an application is deployed in a region (i.e., deployed on infrastructure associated with that region) where it is most heavily used, because using nearby resources is faster than using distant resources. Applications can also be deployed in different regions for various reasons, such as redundancy to mitigate the risk of region-wide events such as large weather systems or earthquakes, to meet varying requirements for legal jurisdictions, tax domains, and other business or social criteria, and the like.

The data centers within a region can be further organized and subdivided into availability domains (ADs). An availability domain may correspond to one or more data centers located within a region. A region can be composed of one or more availability domains. In such a distributed environment, CSPI resources are either region-specific, such as a virtual cloud network (VCN), or availability domain-specific, such as a compute instance.

ADs within a region are isolated from each other, fault tolerant, and are configured such that they are very unlikely to fail simultaneously. This is achieved by the ADs not sharing critical infrastructure resources such as networking, physical cables, cable paths, cable entry points, etc., such that a failure at one AD within a region is unlikely to impact the availability of the other ADs within the same region. The ADs within the same region may be connected to each other by a low latency, high bandwidth network, which makes it possible to provide high-availability connectivity to other networks (e.g., the Internet, customers' on-premises networks, etc.) and to build replicated systems in multiple ADs for both high-availability and disaster recovery. Cloud services use multiple ADs to ensure high availability and to protect against resource failure. As the infrastructure provided by the IaaS provider grows, more regions and ADs may be added with additional capacity. Traffic between availability domains is usually encrypted.

In certain embodiments, regions are grouped into realms. A realm is a logical collection of regions. Realms are isolated from each other and do not share any data. Regions in the same realm may communicate with each other, but regions in different realms cannot. A customer's tenancy or account with the CSP exists in a single realm and can be spread across one or more regions that belong to that realm. Typically, when a customer subscribes to an IaaS service, a tenancy or account is created for that customer in the customer-specified region (referred to as the “home” region) within a realm. A customer can extend the customer's tenancy across one or more other regions within the realm. A customer cannot access regions that are not in the realm where the customer's tenancy exists.

An IaaS provider can provide multiple realms, each realm catered to a particular set of customers or users. For example, a commercial realm may be provided for commercial customers. As another example, a realm may be provided for a specific country for customers within that country. As yet another example, a government realm may be provided for a government, and the like. For example, the government realm may be catered for a specific government and may have a heightened level of security than a commercial realm. For example, Oracle Cloud Infrastructure (OCI) currently offers a realm for commercial regions and two realms (e.g., FedRAMP authorized and IL5 authorized) for government cloud regions.

In certain embodiments, an AD can be subdivided into one or more fault domains. A fault domain is a grouping of infrastructure resources within an AD to provide anti-affinity. Fault domains allow for the distribution of compute instances such that the instances are not on the same physical hardware within a single AD. This is known as anti-affinity. A fault domain refers to a set of hardware components (computers, switches, and more) that share a single point of failure. A compute pool is logically divided up into fault domains. Due to this, a hardware failure or compute hardware maintenance event that affects one fault domain does not affect instances in other fault domains. Depending on the embodiment, the number of fault domains for each AD may vary. For instance, in certain embodiments each AD contains three fault domains. A fault domain acts as a logical data center within an AD.

When a customer subscribes to an IaaS service, resources from CSPI are provisioned for the customer and associated with the customer's tenancy. The customer can use these provisioned resources to build private networks and deploy resources on these networks. The customer networks that are hosted in the cloud by the CSPI are referred to as virtual cloud networks (VCNs). A customer can set up one or more virtual cloud networks (VCNs) using CSPI resources allocated for the customer. A VCN is a virtual or software defined private network. The customer resources that are deployed in the customer's VCN can include compute instances (e.g., virtual machines, bare-metal instances) and other resources. These compute instances may represent various customer workloads such as applications, load balancers, databases, and the like. A compute instance deployed on a VCN can communicate with publicly accessible endpoints (“public endpoints”) over a public network such as the Internet, with other instances in the same VCN or other VCNs (e.g., the customer's other VCNs, or VCNs not belonging to the customer), with the customer's on-premise data centers or networks, and with service endpoints, and other types of endpoints.

The CSP may provide various services using the CSPI. In some instances, customers of CSPI may themselves act like service providers and provide services using CSPI resources. A service provider may expose a service endpoint, which is characterized by identification information (e.g., an IP Address, a DNS name and port). A customer's resource (e.g., a compute instance) can consume a particular service by accessing a service endpoint exposed by the service for that particular service. These service endpoints are generally endpoints that are publicly accessible by users using public IP addresses associated with the endpoints via a public communication network such as the Internet. Network endpoints that are publicly accessible are also sometimes referred to as public endpoints.

In certain embodiments, a service provider may expose a service via an endpoint (sometimes referred to as a service endpoint) for the service. Customers of the service can then use this service endpoint to access the service. In certain implementations, a service endpoint provided for a service can be accessed by multiple customers that intend to consume that service. In other implementations, a dedicated service endpoint may be provided for a customer such that only that customer can access the service using that dedicated service endpoint.

10 0 16 In certain embodiments, when a VCN is created, it is associated with a private overlay Classless Inter-Domain Routing (CIDR) address space, which is a range of private overlay IP addresses that are assigned to the VCN (e.g.,./). A VCN includes associated subnets, route tables, and gateways. A VCN resides within a single region but can span one or more or all of the region's availability domains. A gateway is a virtual interface that is configured for a VCN and enables communication of traffic to and from the VCN to one or more endpoints outside the VCN. One or more different types of gateways may be configured for a VCN to enable communication to and from different types of endpoints.

A VCN can be subdivided into one or more sub-networks such as one or more subnets. A subnet is thus a unit of configuration or a subdivision that can be created within a VCN. A VCN can have one or multiple subnets. Each subnet within a VCN is associated with a contiguous range of overlay IP addresses (e.g., 10.0.0.0/24 and 10.0.1.0/24) that do not overlap with other subnets in that VCN, and which represent an address space subset within the address space of the VCN.

Each compute instance is associated with a virtual network interface card (VNIC), that enables the compute instance to participate in a subnet of a VCN. A VNIC is a logical representation of physical Network Interface Card (NIC). In general. a VNIC is an interface between an entity (e.g., a compute instance, a service) and a virtual network. A VNIC exists in a subnet, has one or more associated IP addresses, and associated security rules or policies. A VNIC is equivalent to a Layer-2 port on a switch. A VNIC is attached to a compute instance and to a subnet within a VCN. A VNIC associated with a compute instance enables the compute instance to be a part of a subnet of a VCN and enables the compute instance to communicate (e.g., send and receive packets) with endpoints that are on the same subnet as the compute instance, with endpoints in different subnets in the VCN, or with endpoints outside the VCN. The VNIC associated with a compute instance thus determines how the compute instance connects with endpoints inside and outside the VCN. A VNIC for a compute instance is created and associated with that compute instance when the compute instance is created and added to a subnet within a VCN. For a subnet comprising a set of compute instances, the subnet contains the VNICs corresponding to the set of compute instances, each VNIC attached to a compute instance within the set of computer instances.

Each compute instance is assigned a private overlay IP address via the VNIC associated with the compute instance. This private overlay IP address is assigned to the VNIC that is associated with the compute instance when the compute instance is created and used for routing traffic to and from the compute instance. All VNICs in a given subnet use the same route table, security lists, and DHCP options. As described above, each subnet within a VCN is associated with a contiguous range of overlay IP addresses (e.g., 10.0.0.0/24 and 10.0.1.0/24) that do not overlap with other subnets in that VCN, and which represent an address space subset within the address space of the VCN. For a VNIC on a particular subnet of a VCN, the private overlay IP address that is assigned to the VNIC is an address from the contiguous range of overlay IP addresses allocated for the subnet.

In certain embodiments, a compute instance may optionally be assigned additional overlay IP addresses in addition to the private overlay IP address, such as, for example, one or more public IP addresses if in a public subnet. These multiple addresses are assigned either on the same VNIC or over multiple VNICs that are associated with the compute instance. Each instance however has a primary VNIC that is created during instance launch and is associated with the overlay private IP address assigned to the instance—this primary VNIC cannot be removed. Additional VNICs, referred to as secondary VNICs, can be added to an existing instance in the same availability domain as the primary VNIC. All the VNICs are in the same availability domain as the instance. A secondary VNIC can be in a subnet in the same VCN as the primary VNIC, or in a different subnet that is either in the same VCN or a different one.

A compute instance may optionally be assigned a public IP address if it is in a public subnet. A subnet can be designated as either a public subnet or a private subnet at the time the subnet is created. A private subnet means that the resources (e.g., compute instances) and associated VNICs in the subnet cannot have public overlay IP addresses. A public subnet means that the resources and associated VNICs in the subnet can have public IP addresses. A customer can designate a subnet to exist either in a single availability domain or across multiple availability domains in a region or realm.

1 FIG. As described above, a VCN may be subdivided into one or more subnets. In certain embodiments, a Virtual Router (VR) configured for the VCN (referred to as the VCN VR or just VR) enables communications between the subnets of the VCN. For a subnet within a VCN, the VR represents a logical gateway for that subnet that enables the subnet (i.e., the compute instances on that subnet) to communicate with endpoints on other subnets within the VCN, and with other endpoints outside the VCN. The VCN VR is a logical entity that is configured to route traffic between VNICs in the VCN and virtual gateways (“gateways”) associated with the VCN. Gateways are further described below with respect to. A VCN VR is a Layer-3/IP Layer concept. In one embodiment, there is one VCN VR for a VCN where the VCN VR has potentially an unlimited number of ports addressed by IP addresses, with one port for each subnet of the VCN. In this manner, the VCN VR has a different IP address for each subnet in the VCN that the VCN VR is attached to. The VR is also connected to the various gateways configured for a VCN. In certain embodiments, a particular overlay IP address from the overlay IP address range for a subnet is reserved for a port of the VCN VR for that subnet. For example, consider a VCN having two subnets with associated address ranges 10.0/16 and 10.1/16, respectively. For the first subnet within the VCN with address range 10.0/16, an address from this range is reserved for a port of the VCN VR for that subnet. In some instances, the first IP address from the range may be reserved for the VCN VR. For example, for the subnet with overlay IP address range 10.0/16, IP address 10.0.0.1 may be reserved for a port of the VCN VR for that subnet. For the second subnet within the same VCN with address range 10.1/16, the VCN VR may have a port for that second subnet with IP address 10.1.0.1. The VCN VR has a different IP address for each of the subnets in the VCN.

In some other embodiments, each subnet within a VCN may have its own associated VR that is addressable by the subnet using a reserved or default IP address associated with the VR. The reserved or default IP address may, for example, be the first IP address from the range of IP addresses associated with that subnet. The VNICs in the subnet can communicate (e.g., send and receive packets) with the VR associated with the subnet using this default or reserved IP address. In such an embodiment, the VR is the ingress/egress point for that subnet. The VR associated with a subnet within the VCN can communicate with other VRs associated with other subnets within the VCN. The VRs can also communicate with gateways associated with the VCN. The VR function for a subnet is running on or executed by one or more NVDs executing VNICs functionality for VNICs in the subnet.

Route tables, security rules, and DHCP options may be configured for a VCN. Route tables are virtual route tables for the VCN and include rules to route traffic from subnets within the VCN to destinations outside the VCN by way of gateways or specially configured instances. A VCN's route tables can be customized to control how packets are forwarded/routed to and from the VCN. DHCP options refers to configuration information that is automatically provided to the instances when they boot up.

0 0 0 0 0 22 Security rules configured for a VCN represent overlay firewall rules for the VCN. The security rules can include ingress and egress rules, and specify the types of traffic (e.g., based upon protocol and port) that is allowed in and out of the instances within the VCN. The customer can choose whether a given rule is stateful or stateless. For instance, the customer can allow incoming SSH traffic from anywhere to a set of instances by setting up a stateful ingress rule with source CIDR.../, and destination TCP port. Security rules can be implemented using network security groups or security lists. A network security group consists of a set of security rules that apply only to the resources in that group. A security list, on the other hand, includes rules that apply to all the resources in any subnet that uses the security list. A VCN may be provided with a default security list with default security rules. DHCP options configured for a VCN provide configuration information that is automatically provided to the instances in the VCN when the instances boot up.

In certain embodiments, the configuration information for a VCN is determined and stored by a VCN Control Plane. The configuration information for a VCN may include, for example, information about the address range associated with the VCN, subnets within the VCN and associated information, one or more VRs associated with the VCN, compute instances in the VCN and associated VNICs, NVDs executing the various virtualization network functions (e.g., VNICs, VRs, gateways) associated with the VCN, state information for the VCN, and other VCN-related information. In certain embodiments, a VCN Distribution Service publishes the configuration information stored by the VCN Control Plane, or portions thereof, to the NVDs. The distributed information may be used to update information (e.g., forwarding tables, routing tables, etc.) stored and used by the NVDs to forward packets to and from the compute instances in the VCN.

12 13 14 15 FIGS.,,, and 1216 1316 1416 1516 In certain embodiments, the creation of VCNs and subnets are handled by a VCN Control Plane (CP), and the launching of compute instances is handled by a Compute Control Plane. The Compute Control Plane is responsible for allocating the physical resources for the compute instance and then calls the VCN Control Plane to create and attach VNICs to the compute instance. The VCN CP also sends VCN data mappings to the VCN data plane that is configured to perform packet forwarding and routing functions. In certain embodiments, the VCN CP provides a distribution service that is responsible for providing updates to the VCN data plane. Examples of a VCN Control Plane are also depicted in(see references,,, and) and described below.

A customer may create one or more VCNs using resources hosted by CSPI. A compute instance deployed on a customer VCN may communicate with different endpoints. These endpoints can include endpoints that are hosted by CSPI and endpoints outside CSPI.

1 2 3 4 5 12 16 FIGS.,,,,, and- 1 FIG. 1 FIG. 1 FIG. 1 FIG. 1 FIG. 100 100 Various different architectures for implementing cloud-based service using CSPI are depicted in, and are described below.is a high-level diagram of a distributed environmentshowing an overlay or customer VCN hosted by CSPI according to certain embodiments. The distributed environment depicted inincludes multiple components in the overlay network. Distributed environmentdepicted inis merely an example and is not intended to unduly limit the scope of claimed embodiments. Many variations, alternatives, and modifications are possible. For example, in some implementations, the distributed environment depicted inmay have more or fewer systems or components than those shown in, may combine two or more systems, or may have a different configuration or arrangement of systems.

1 FIG. 1 FIG. 100 101 101 101 102 102 104 As shown in the example depicted in, distributed environmentcomprises CSPIthat provides services and resources that customers can subscribe to and use to build their virtual cloud networks (VCNs). In certain embodiments, CSPIoffers IaaS services to subscribing customers. The data centers within CSPImay be organized into one or more regions. One example region “Region US”is shown in. A customer has configured a customer VCN c/o Oracle International Corporation for region. The customer may deploy various compute instances on VCN, where the compute instances may include virtual machines or bare metal instances. Examples of instances include applications, database, load balancers, and the like.

1 FIG. 1 FIG. 104 105 104 105 104 104 105 104 105 In the embodiment depicted in, customer VCNcomprises two subnets, namely, “Subnet-1” and “Subnet-2”, each subnet with its own CIDR IP address range. In, the overlay IP address range for Subnet-1 is 10.0/16 and the address range for Subnet-2 is 10.1/16. A VCN Virtual Routerrepresents a logical gateway for the VCN that enables communications between subnets of the VCN, and with other endpoints outside the VCN. VCN VRis configured to route traffic between VNICs in VCNand gateways associated with VCN. VCN VRprovides a port for each subnet of VCN. For example, VRmay provide a port with IP address 10.0.0.1 for Subnet-1 and a port with IP address 10.1.0.1 for Subnet-2.

101 1 2 2 1 1 2 2 1 2 105 105 1 FIG. 1 FIG. Multiple compute instances may be deployed on each subnet, where the compute instances can be virtual machine instances, and/or bare metal instances. The compute instances in a subnet may be hosted by one or more host machines within CSPI. A compute instance participates in a subnet via a VNIC associated with the compute instance. For example, as shown in, a compute instance Cis part of Subnet-1 via a VNIC associated with the compute instance. Likewise, compute instance Cis part of Subnet-1 via a VNIC associated with C. In a similar manner, multiple compute instances, which may be virtual machine instances or bare metal instances, may be part of Subnet-1. Via its associated VNIC, each compute instance is assigned a private overlay IP address and a MAC address. For example, in, compute instance Chas an overlay IP address of 10.0.0.2 and a MAC address of M, while compute instance Chas a private overlay IP address of 10.0.0.3 and a MAC address of M. Each compute instance in Subnet-1, including compute instances Cand C, has a default route to VCN VRusing IP address 10.0.0.1, which is the IP address for a port of VCN VRfor Subnet-1.

1 FIG. 1 FIG. 1 2 1 1 2 2 1 2 105 105 Subnet-2 can have multiple compute instances deployed on it, including virtual machine instances and/or bare metal instances. For example, as shown in, compute instances Dand Dare part of Subnet-2 via VNICs associated with the respective compute instances. In the embodiment depicted in, compute instance Dhas an overlay IP address of 10.1.0.2 and a MAC address of MM, while compute instance Dhas a private overlay IP address of 10.1.0.3 and a MAC address of MM. Each compute instance in Subnet-2, including compute instances Dand D, has a default route to VCN VRusing IP address 10.1.0.1, which is the IP address for a port of VCN VRfor Subnet-2.

104 VCN Amay also include one or more load balancers. For example, a load balancer may be provided for a subnet and may be configured to load balance traffic across multiple compute instances on the subnet. A load balancer may also be provided to load balance traffic across subnets in the VCN.

104 200 200 101 106 110 110 108 101 101 101 116 118 114 A particular compute instance deployed on VCNcan communicate with various different endpoints. These endpoints may include endpoints that are hosted by CSPIand endpoints outside CSPI. Endpoints that are hosted by CSPImay include: an endpoint on the same subnet as the particular compute instance (e.g., communications between two compute instances in Subnet-1); an endpoint on a different subnet but within the same VCN (e.g., communication between a compute instance in Subnet-1 and a compute instance in Subnet-2); an endpoint in a different VCN in the same region (e.g., communications between a compute instance in Subnet-1 and an endpoint in a VCN in the same regionor, communications between a compute instance in Subnet-1 and an endpoint in service networkin the same region); or an endpoint in a VCN in a different region (e.g., communications between a compute instance in Subnet-1 and an endpoint in a VCN in a different region). A compute instance in a subnet hosted by CSPImay also communicate with endpoints that are not hosted by CSPI(i.e., are outside CSPI). These outside endpoints include endpoints in the customer's on-premises network, endpoints within other remote cloud hosted networks, public endpointsaccessible via a public network such as the Internet, and other endpoints.

1 2 Communications between compute instances on the same subnet are facilitated using VNICs associated with the source compute instance and the destination compute instance. For example, compute instance Cin Subnet-1 may want to send packets to compute instance Cin Subnet-1. For a packet originating at a source compute instance and whose destination is another compute instance in the same subnet, the packet is first processed by the VNIC associated with the source compute instance. Processing performed by the VNIC associated with the source compute instance can include determining destination information for the packet from the packet headers, identifying any policies (e.g., security lists) configured for the VNIC associated with the source compute instance, determining a next hop for the packet, performing any packet encapsulation/decapsulation functions as needed, and then forwarding/routing the packet to the next hop with the goal of facilitating communication of the packet to its intended destination. When the destination compute instance is in the same subnet as the source compute instance, the VNIC associated with the source compute instance is configured to identify the VNIC associated with the destination compute instance and forward the packet to that VNIC for processing. The VNIC associated with the destination compute instance is then executed and forwards the packet to the destination compute instance.

1 1 1 1 105 105 1 1 1 FIG. For a packet to be communicated from a compute instance in a subnet to an endpoint in a different subnet in the same VCN, the communication is facilitated by the VNICs associated with the source and destination compute instances and the VCN VR. For example, if compute instance Cin Subnet-1 inwants to send a packet to compute instance Din Subnet-2, the packet is first processed by the VNIC associated with compute instance C. The VNIC associated with compute instance Cis configured to route the packet to the VCN VRusing default route or port 10.0.0.1 of the VCN VR. VCN VRis configured to route the packet to Subnet-2 using port 10.1.0.1. The packet is then received and processed by the VNIC associated with Dand the VNIC forwards the packet to compute instance D.

104 104 105 104 104 For a packet to be communicated from a compute instance in VCNto an endpoint that is outside VCN, the communication is facilitated by the VNIC associated with the source compute instance, VCN VR, and gateways associated with VCN. One or more types of gateways may be associated with VCN. A gateway is an interface between a VCN and another endpoint, where another endpoint is outside the VCN. A gateway is a Layer-3/IP layer concept and enables a VCN to communicate with endpoints outside the VCN. A gateway thus facilitates traffic flow between a VCN and other VCNs or networks. Various different types of gateways may be configured for a VCN to facilitate different types of communications with different types of endpoints. Depending upon the gateway, the communications may be over public networks (e.g., the Internet) or over private networks. Various communication protocols may be used for these communications.

1 104 1 1 1 105 104 105 104 105 105 122 104 For example, compute instance Cmay want to communicate with an endpoint outside VCN. The packet may be first processed by the VNIC associated with source compute instance C. The VNIC processing determines that the destination for the packet is outside the Subnet-1 of C. The VNIC associated with Cmay forward the packet to VCN VRfor VCN. VCN VRthen processes the packet and as part of the processing, based upon the destination for the packet, determines a particular gateway associated with VCNas the next hop for the packet. VCN VRmay then forward the packet to the particular identified gateway. For example, if the destination is an endpoint within the customer's on-premise network, then the packet may be forwarded by VCN VRto Dynamic Routing Gateway (DRG) gatewayconfigured for VCN. The packet may then be forwarded from the gateway to a next hop to facilitate communication of the packet to it final intended destination.

1 FIG. 12 13 14 15 FIGS.,,, and 1 FIG. 1 FIG. 1234 1236 1238 1334 1336 1338 1434 1436 1438 1534 1536 1538 122 104 104 116 108 101 118 101 116 116 116 104 101 116 104 104 101 116 122 124 116 101 104 124 116 124 126 101 122 Various different types of gateways may be configured for a VCN. Examples of gateways that may be configured for a VCN are depicted inand described below. Examples of gateways associated with a VCN are also depicted in(for example, gateways referenced by reference numbers,,,,,,,,,,, and) and described below. As shown in the embodiment depicted in, a Dynamic Routing Gateway (DRG)may be added to or be associated with customer VCNand provides a path for private network traffic communication between customer VCNand another endpoint, where another endpoint can be the customer's on-premise network, a VCNin a different region of CSPI, or other remote cloud networksnot hosted by CSPI. Customer on-premise networkmay be a customer network or a customer data center built using the customer's resources. Access to customer on-premise networkis generally very restricted. For a customer that has both a customer on-premise networkand one or more VCNsdeployed or hosted in the cloud by CSPI, the customer may want their on-premise networkand their cloud based VCNto be able to communicate with each other. This enables a customer to build an extended hybrid environment encompassing the customer's VCNhosted by CSPIand their on-premises network. DRGenables this communication. To enable such communications, a communication channelis set up where one endpoint of the channel is in customer on-premise networkand the other endpoint is in CSPIand connected to customer VCN. Communication channelcan be over public communication networks such as the Internet or private communication networks. Various different communication protocols may be used such as IPsec VPN technology over a public communication network such as the Internet, Oracle's FastConnect technology that uses a private network instead of a public network, and others. The device or equipment in customer on-premise networkthat forms one end point for communication channelis referred to as the customer premise equipment (CPE), such as CPEdepicted in. On the CSPIside, the endpoint may be a host machine executing DRG.

104 122 108 122 118 101 In certain embodiments, a Remote Peering Connection (RPC) can be added to a DRG, which allows a customer to peer one VCN with another VCN in a different region. Using such an RPC, customer VCNcan use DRGto connect with a VCNin another region. DRGmay also be used to communicate with other remote cloud networks, not hosted by CSPIsuch as a Microsoft Azure cloud, Amazon AWS cloud, and others.

1 FIG. 120 104 104 114 120 120 104 112 114 120 104 As shown in, an Internet Gateway (IGW)may be configured for customer VCNthe enables a compute instance on VCNto communicate with public endpointsaccessible over a public network such as the Internet. IGWis a gateway that connects a VCN to a public network such as the Internet. IGWenables a public subnet (where the resources in the public subnet have public overlay IP addresses) within a VCN, such as VCN, direct access to public endpointson a public networksuch as the Internet. Using IGW, connections can be initiated from a subnet within VCNor from the Internet.

128 104 104 A Network Address Translation (NAT) gatewaycan be configured for customer's VCNand enables cloud resources in the customer's VCN, which do not have dedicated public overlay IP addresses, access to the Internet and it does so without exposing those resources to direct incoming Internet connections (e.g., L4-L7 connections). This enables a private subnet within a VCN, such as private Subnet-1 in VCN, with private access to public endpoints on the Internet. In NAT gateways, connections can be initiated only from the private subnet to the public Internet and not from the Internet to the private subnet.

126 104 104 110 110 104 110 In certain embodiments, a Service Gateway (SGW)can be configured for customer VCNand provides a path for private network traffic between VCNand supported services endpoints in a service network. In certain embodiments, service networkmay be provided by the CSP and may provide various services. An example of such a service network is Oracle's Services Network, which provides various services that can be used by customers. For example, a compute instance (e.g., a database system) in a private subnet of customer VCNcan back up data to a service endpoint (e.g., Object Storage) without needing public IP addresses or access to the Internet. In certain embodiments, a VCN can have only one SGW, and connections can only be initiated from a subnet within the VCN and not from service network. If a VCN is peered with another, resources in the other VCN typically cannot access the SGW. Resources in on-premises networks that are connected to a VCN with FastConnect or VPN Connect can also use the service gateway configured for that VCN.

126 In certain implementations, SGWuses the concept of a service Classless Inter-Domain Routing (CIDR) label, which is a string that represents all the regional public IP address ranges for the service or group of services of interest. The customer uses the service CIDR label when they configure the SGW and related route rules to control traffic to the service. The customer can optionally utilize it when configuring security rules without needing to adjust them if the service's public IP addresses change in the future.

132 104 104 116 A Local Peering Gateway (LPG)is a gateway that can be added to customer VCNand enables VCNto peer with another VCN in the same region. Peering means that the VCNs communicate using private IP addresses, without the traffic traversing a public network such as the Internet or without routing the traffic through the customer's on-premises network. In preferred embodiments, a VCN has a separate LPG for each peering it establishes. Local Peering or VCN Peering is a common practice used to establish network connectivity between different applications or infrastructure management functions.

110 126 Service providers, such as providers of services in service network, may provide access to services using different access models. According to a public access model, services may be exposed as public endpoints that are publicly accessible by compute instance in a customer VCN via a public network such as the Internet and or may be privately accessible via SGW. According to a specific private access model, services are made accessible as private IP endpoints in a private subnet in the customer's VCN. This is referred to as a Private Endpoint (PE) access and enables a service provider to expose their service as an instance in the customer's private network. A Private Endpoint resource represents a service within the customer's VCN. Each PE manifests as a VNIC (referred to as a PE-VNIC, with one or more private IPs) in a subnet chosen by the customer in the customer's VCN. A PE thus provides a way to present a service within a private customer VCN subnet using a VNIC. Since the endpoint is exposed as a VNIC, all the features associates with a VNIC such as routing rules, security lists, etc., are now available for the PE VNIC.

A service provider can register their service to enable access through a PE. The provider can associate policies with the service that restricts the service's visibility to the customer tenancies. A provider can register multiple services under a single virtual IP address (VIP), especially for multi-tenant services. There may be multiple such private endpoints (in multiple VCNs) that represent the same service.

130 110 130 130 Compute instances in the private subnet can then use the PE VNIC's private IP address or the service DNS name to access the service. Compute instances in the customer VCN can access the service by sending traffic to the private IP address of the PE in the customer VCN. A Private Access Gateway (PAGW)is a gateway resource that can be attached to a service provider VCN (e.g., a VCN in service network) that acts as an ingress/egress point for all traffic from/to customer subnet private endpoints. PAGWenables a provider to scale the number of PE connections without utilizing its internal IP address resources. A provider needs only configure one PAGW for any number of services registered in a single VCN. Providers can represent a service as a private endpoint in multiple VCNs of one or more customers. From the customer's perspective, the PE VNIC, which, instead of being attached to a customer's instance, appears attached to the service with which the customer wishes to interact. The traffic destined to the private endpoint is routed via PAGWto the service. These are referred to as customer-to-service private connections (C2S connections).

132 The PE concept can also be used to extend the private access for the service to customer's on-premises networks and data centers, by allowing the traffic to flow through FastConnect/IPsec links and the private endpoint in the customer VCN. Private access for the service can also be extended to the customer's peered VCNs, by allowing the traffic to flow between LPGand the PE in the customer's VCN.

104 104 120 104 126 128 A customer can control routing in a VCN at the subnet level, so the customer can specify which subnets in the customer's VCN, such as VCN, use each gateway. A VCN's route tables are used to decide if traffic is allowed out of a VCN through a particular gateway. For example, in a particular instance, a route table for a public subnet within customer VCNmay send non-local traffic through IGW. The route table for a private subnet within the same customer VCNmay send traffic destined for CSP services through SGW. All remaining traffic may be sent via the NAT gateway. Route tables only control traffic going out of a VCN.

22 3389 Security lists associated with a VCN are used to control traffic that comes into a VCN via a gateway via inbound connections. All resources in a subnet use the same route table and security lists. Security lists may be used to control specific types of traffic allowed in and out of instances in a subnet of a VCN. Security list rules may comprise ingress (inbound) and egress (outbound) rules. For example, an ingress rule may specify an allowed source address range, while an egress rule may specify an allowed destination address range. Security rules may specify a particular protocol (e.g., TCP, ICMP), a particular port (e.g.,for SSH,for Windows RDP), etc. In certain implementations, an instance's operating system may enforce its own firewall rules that are aligned with the security list rules. Rules may be stateful (e.g., a connection is tracked, and the response is automatically allowed without an explicit security list rule for the response traffic) or stateless.

104 104 101 Access from a customer VCN (i.e., by a resource or compute instance deployed on VCN) can be categorized as public access, private access, or dedicated access. Public access refers to an access model where a public IP address or a NAT is used to access a public endpoint. Private access enables customer workloads in VCNwith private IP addresses (e.g., resources in a private subnet) to access services without traversing a public network such as the Internet. In certain embodiments, CSPIenables customer VCN workloads with private IP addresses to access the (public service endpoints of) services using a service gateway. A service gateway thus offers a private access model by establishing a virtual link between the customer's VCN and the service's public endpoint residing outside the customer's private network.

Additionally, CSPI may offer dedicated public access using technologies such as FastConnect public peering where customer on-premises instances can access one or more services in a customer VCN using a FastConnect connection and without traversing a public network such as the Internet. CSPI also may also offer dedicated private access using FastConnect private peering where customer on-premises instances with private IP addresses can access the customer's VCN workloads using a FastConnect connection. FastConnect is a network connectivity alternative to using the public Internet to connect a customer's on-premise network to CSPI and its services. FastConnect provides an easy, elastic, and economical way to create a dedicated and private connection with higher bandwidth options and a more reliable and consistent networking experience when compared to Internet-based connections.

1 FIG. 2 FIG. 200 200 200 200 200 and the accompanying description above describes various virtualized components in an example virtual network. As described above, the virtual network is built on the underlying physical or substrate network.depicts a simplified architectural diagram of the physical components in the physical network within CSPIthat provide the underlay for the virtual network according to certain embodiments. As shown, CSPIprovides a distributed environment comprising components and resources (e.g., compute, memory, and networking resources) provided by a cloud service provider (CSP). These components and resources are used to provide cloud services (e.g., IaaS services) to subscribing customers, i.e., customers that have subscribed to one or more services provided by the CSP. Based upon the services subscribed to by a customer, a subset of resources (e.g., compute, memory, and networking resources) of CSPIare provisioned for the customer. Customers can then build their own cloud-based (i.e., CSPI-hosted) customizable and private virtual networks using physical compute, memory, and networking resources provided by CSPI. As previously indicated, these customer networks are referred to as virtual cloud networks (VCNs). A customer can deploy one or more customer resources, such as compute instances, on these customer VCNs. Compute instances can be in the form of virtual machines, bare metal instances, and the like. CSPIprovides infrastructure and a set of complementary cloud services that enable customers to build and run a wide range of applications and services in a highly available hosted environment.

2 FIG. 1 FIG. 2 FIG. 1 FIG. 2 FIG. 1 FIG. 2 FIG. 200 202 206 208 210 212 214 216 218 218 In the example embodiment depicted in, the physical components of CSPIinclude one or more physical host machines or physical servers (e.g.,,,), network virtualization devices (NVDs) (e.g.,,), top-of-rack (TOR) switches (e.g.,,), and a physical network (e.g.,), and switches in physical network. The physical host machines or servers may host and execute various compute instances that participate in one or more subnets of a VCN. The compute instances may include virtual machine instances, and bare metal instances. For example, the various compute instances depicted inmay be hosted by the physical host machines depicted in. The virtual machine compute instances in a VCN may be executed by one host machine or by multiple different host machines. The physical host machines may also host virtual host machines, container-based hosts or functions, and the like. The VNICs and VCN VR depicted inmay be executed by the NVDs depicted in. The gateways depicted inmay be executed by the host machines and/or by the NVDs depicted in.

The host machines or servers may execute a hypervisor (also referred to as a virtual machine monitor or VMM) that creates and enables a virtualized environment on the host machines. The virtualization or virtualized environment facilitates cloud-based computing. One or more compute instances may be created, executed, and managed on a host machine by a hypervisor on that host machine. The hypervisor on a host machine enables the physical computing resources of the host machine (e.g., compute, memory, and networking resources) to be shared between the various compute instances executed by the host machine.

2 FIG. 2 FIG. 2 FIG. 202 208 260 266 260 202 202 202 For example, as depicted in, host machinesandexecute hypervisorsand, respectively. These hypervisors may be implemented using software, firmware, or hardware, or combinations thereof. Typically, a hypervisor is a process or a software layer that sits on top of the host machine's operating system (OS), which in turn executes on the hardware processors of the host machine. The hypervisor provides a virtualized environment by enabling the physical computing resources (e.g., processing resources such as processors/cores, memory resources, networking resources) of the host machine to be shared among the various virtual machine compute instances executed by the host machine. For example, in, hypervisormay sit on top of the OS of host machineand enables the computing resources (e.g., processing, memory, and networking resources) of host machineto be shared between compute instances (e.g., virtual machines) executed by host machine. A virtual machine can have its own operating system (referred to as a guest operating system), which may be the same as or different from the OS of the host machine. The operating system of a virtual machine executed by a host machine may be the same as or different from the operating system of another virtual machine executed by the same host machine. A hypervisor thus enables multiple operating systems to be executed alongside each other while sharing the same computing resources of the host machine. The host machines depicted inmay have the same or different types of hypervisors.

2 FIG. 268 202 274 208 206 A compute instance can be a virtual machine instance or a bare metal instance. In, compute instanceson host machineandon host machineare examples of virtual machine instances. Host machineis an example of a bare metal instance that is provided to a customer.

In certain instances, an entire host machine may be provisioned to a single customer, and all of the one or more compute instances (either virtual machines or bare metal instance) hosted by that host machine belong to that same customer. In other instances, a host machine may be shared between multiple customers (i.e., multiple tenants). In such a multi-tenancy scenario, a host machine may host virtual machine compute instances belonging to different customers. These compute instances may be members of different VCNs of different customers. In certain embodiments, a bare metal compute instance is hosted by a bare metal server without a hypervisor. When a bare metal compute instance is provisioned, a single customer or tenant maintains control of the physical CPU, memory, and network interfaces of the host machine hosting the bare metal instance and the host machine is not shared with other customers or tenants.

2 FIG. 202 268 276 276 210 202 272 206 280 212 206 284 274 208 284 212 208 As previously described, each compute instance that is part of a VCN is associated with a VNIC that enables the compute instance to become a member of a subnet of the VCN. The VNIC associated with a compute instance facilitates the communication of packets or frames to and from the compute instance. A VNIC is associated with a compute instance when the compute instance is created. In certain embodiments, for a compute instance executed by a host machine, the VNIC associated with that compute instance is executed by an NVD connected to the host machine. For example, in, host machineexecutes a virtual machine compute instancethat is associated with VNIC, and VNICis executed by NVDconnected to host machine. As another example, bare metal instancehosted by host machineis associated with VNICthat is executed by NVDconnected to host machine. As yet another example, VNICis associated with compute instanceexecuted by host machine, and VNICis executed by NVDconnected to host machine.

2 FIG. 210 277 268 212 283 206 208 For compute instances hosted by a host machine, an NVD connected to that host machine also executes VCN VRs corresponding to VCNs of which the compute instances are members. For example, in the embodiment depicted in, NVDexecutes VCN VRcorresponding to the VCN of which compute instanceis a member. NVDmay also execute one or more VCN VRscorresponding to VCNs corresponding to the compute instances hosted by host machinesand.

A host machine may include one or more network interface cards (NIC) that enable the host machine to be connected to other devices. A NIC on a host machine may provide one or more ports (or interfaces) that enable the host machine to be communicatively connected to another device. For example, a host machine may be connected to an NVD using one or more ports (or interfaces) provided on the host machine and on the NVD. A host machine may also be connected to other devices such as another host machine.

2 FIG. 202 210 220 234 232 202 236 210 206 212 224 246 244 206 248 212 208 212 226 252 250 208 254 212 For example, in, host machineis connected to NVDusing linkthat extends between a portprovided by a NICof host machineand between a portof NVD. Host machineis connected to NVDusing linkthat extends between a portprovided by a NICof host machineand between a portof NVD. Host machineis connected to NVDusing linkthat extends between a portprovided by a NICof host machineand between a portof NVD.

218 210 212 214 216 228 230 220 224 226 228 230 2 FIG. The NVDs are in turn connected via communication links to top-of-the-rack (TOR) switches, which are connected to physical network(also referred to as the switch fabric). In certain embodiments, the links between a host machine and an NVD, and between an NVD and a TOR switch are Ethernet links. For example, in, NVDsandare connected to TOR switchesand, respectively, using linksand. In certain embodiments, the links,,,, andare Ethernet links. The collection of host machines and NVDs that are connected to a TOR is sometimes referred to as a rack.

218 218 218 214 216 218 5 FIG. Physical networkprovides a communication fabric that enables TOR switches to communicate with each other. Physical networkcan be a multi-tiered network. In certain implementations, physical networkis a multi-tiered Clos network of switches, with TOR switchesandrepresenting the leaf level nodes of the multi-tiered and multi-node physical switching network. Different Clos network configurations are possible including but not limited to a 2-tier network, a 3-tier network, a 4-tier network, a 5-tier network, and in general a “n”-tiered network. An example of a Clos network is depicted inand described below.

2 FIG. 2 FIG. 202 210 232 202 206 208 212 244 250 Various different connection configurations are possible between host machines and NVDs such as one-to-one configuration, many-to-one configuration, one-to-many configuration, and others. In a one-to-one configuration implementation, each host machine is connected to its own separate NVD. For example, in, host machineis connected to NVDvia NICof host machine. In a many-to-one configuration, multiple host machines are connected to one NVD. For example, in, host machinesandare connected to the same NVDvia NICsand, respectively.

3 FIG. 3 FIG. 300 302 304 306 308 300 310 306 320 312 308 322 306 308 320 322 302 310 312 310 314 312 316 310 312 314 316 314 316 318 In a one-to-many configuration, one host machine is connected to multiple NVDs.shows an example within CSPIwhere a host machine is connected to multiple NVDs. As shown in, host machinecomprises a network interface card (NIC)that includes multiple portsand. Host machineis connected to a first NVDvia portand linkand connected to a second NVDvia portand link. Portsandmay be Ethernet ports and the linksandbetween host machineand NVDsandmay be Ethernet links. NVDis in turn connected to a first TOR switchand NVDis connected to a second TOR switch. The links between NVDsand, and TOR switchesandmay be Ethernet links. TOR switchesandrepresent the Tier-0 switching devices in multi-tiered physical network.

3 FIG. 318 302 314 310 302 316 312 302 302 302 The arrangement depicted inprovides two separate physical network paths to and from physical switch networkto host machine: a first path traversing TOR switchto NVDto host machine, and a second path traversing TOR switchto NVDto host machine. The separate paths provide for enhanced availability (referred to as high availability) of host machine. If there are problems in one of the paths (e.g., a link in one of the paths goes down) or devices (e.g., a particular NVD is not functioning), then the other path may be used for communications to/from host machine.

3 FIG. In the configuration depicted in, the host machine is connected to two different NVDs using two different ports provided by a NIC of the host machine. In other embodiments, a host machine may include multiple NICs that enable connectivity of the host machine to multiple NVDs.

2 FIG. Referring back to, an NVD is a physical device or component that performs one or more network and/or storage virtualization functions. An NVD may be any device with one or more processing units (e.g., CPUs, Network Processing Units (NPUs), FPGAs, packet processing pipelines, etc.), memory including cache, and ports. The various virtualization functions may be performed by software/firmware executed by the one or more processing units of the NVD.

2 FIG. 210 212 202 206 208 An NVD may be implemented in various different forms. For example, in certain embodiments, an NVD is implemented as an interface card referred to as a smartNIC or an intelligent NIC with an embedded processor onboard. A smartNIC is a separate device from the NICs on the host machines. In, the NVDsandmay be implemented as smartNICs that are connected to host machines, and host machinesand, respectively.

200 A smartNIC is however just one example of an NVD implementation. Various other implementations are possible. For example, in some other implementations, an NVD or one or more functions performed by the NVD may be incorporated into or performed by one or more host machines, one or more TOR switches, and other components of CSPI. For example, an NVD may be embodied in a host machine where the functions performed by an NVD are performed by the host machine. As another example, an NVD may be part of a TOR switch, or a TOR switch may be configured to perform functions performed by an NVD that enables the TOR switch to perform various complex packet transformations that are used for a public cloud. A TOR that performs the functions of an NVD is sometimes referred to as a smart TOR. In yet other implementations, where virtual machines (VMs) instances, but not bare metal (BM) instances, are offered to customers, functions performed by an NVD may be implemented inside a hypervisor of the host machine. In some other implementations, some of the functions of the NVD may be offloaded to a centralized service running on a fleet of host machines.

2 FIG. 2 FIG. 2 FIG. 2 FIG. 236 210 248 254 212 256 210 258 212 210 214 228 256 210 214 212 216 230 258 212 216 In certain embodiments, such as when implemented as a smartNIC as shown in, an NVD may comprise multiple physical ports that enable it to be connected to one or more host machines and to one or more TOR switches. A port on an NVD can be classified as a host-facing port (also referred to as a “south port”) or a network-facing or TOR-facing port (also referred to as a “north port”). A host-facing port of an NVD is a port that is used to connect the NVD to a host machine. Examples of host-facing ports ininclude porton NVD, and portsandon NVD. A network-facing port of an NVD is a port that is used to connect the NVD to a TOR switch. Examples of network-facing ports ininclude porton NVD, and porton NVD. As shown in, NVDis connected to TOR switchusing linkthat extends from portof NVDto the TOR switch. Likewise, NVDis connected to TOR switchusing linkthat extends from portof NVDto the TOR switch.

An NVD receives packets and frames from a host machine (e.g., packets and frames generated by a compute instance hosted by the host machine) via a host-facing port and, after performing the necessary packet processing, may forward the packets and frames to a TOR switch via a network-facing port of the NVD. An NVD may receive packets and frames from a TOR switch via a network-facing port of the NVD and, after performing the necessary packet processing, may forward the packets and frames to a host machine via a host-facing port of the NVD.

In certain embodiments, there may be multiple ports and associated links between an NVD and a TOR switch. These ports and links may be aggregated to form a link aggregator group of multiple ports or links (referred to as a LAG). Link aggregation allows multiple physical links between two endpoints (e.g., between an NVD and a TOR switch) to be treated as a single logical link. All the physical links in a given LAG may operate in full-duplex mode at the same speed. LAGs help increase the bandwidth and reliability of the connection between two endpoints. If one of the physical links in the LAG goes down, traffic is dynamically and transparently reassigned to one of the other physical links in the LAG. The aggregated physical links deliver higher bandwidth than each individual link. The multiple ports associated with a LAG are treated as a single logical port. Traffic can be load-balanced across the multiple physical links of a LAG. One or more LAGs may be configured between two endpoints. The two endpoints may be between an NVD and a TOR switch, between a host machine and an NVD, and the like.

An NVD implements or performs network virtualization functions. These functions are performed by software/firmware executed by the NVD. Examples of network virtualization functions include without limitation: packet encapsulation and decapsulation functions; functions for creating a VCN network; functions for implementing network policies such as VCN security list (firewall) functionality; functions that facilitate the routing and forwarding of packets to and from compute instances in a VCN; and the like. In certain embodiments, upon receiving a packet, an NVD is configured to execute a packet processing pipeline for processing the packet and determining how the packet is to be forwarded or routed. As part of this packet processing pipeline, the NVD may execute one or more virtual functions associated with the overlay network such as executing VNICs associated with compute instances in the VCN, executing a Virtual Router (VR) associated with the VCN, the encapsulation and decapsulation of packets to facilitate forwarding or routing in the virtual network, execution of certain gateways (e.g., the Local Peering Gateway), the implementation of Security Lists, Network Security Groups, network address translation (NAT) functionality (e.g., the translation of Public IP to Private IP on a host by host basis), throttling functions, and other functions.

In certain embodiments, the packet processing data path in an NVD may comprise multiple packet pipelines, each composed of a series of packet transformation stages. In certain implementations, upon receiving a packet, the packet is parsed and classified to a single pipeline. The packet is then processed in a linear fashion, one stage after another, until the packet is either dropped or sent out over an interface of the NVD. These stages provide basic functional packet processing building blocks (e.g., validating headers, enforcing throttle, inserting new Layer-2 headers, enforcing L4 firewall, VCN encapsulation/decapsulation, etc.) so that new pipelines can be constructed by composing existing stages, and new functionality can be added by creating new stages and inserting them into existing pipelines.

12 13 14 15 FIGS.,,, and 12 13 14 15 FIGS.,,, and 1216 1316 1416 1516 1218 1318 1418 1518 An NVD may perform both control plane and data plane functions corresponding to a control plane and a data plane of a VCN. Examples of a VCN Control Plane are also depicted in(see references,,, and) and described below. Examples of a VCN Data Plane are depicted in(see references,,, and) and described below. The control plane functions include functions used for configuring a network (e.g., setting up routes and route tables, configuring VNICs, etc.) that controls how data is to be forwarded. In certain embodiments, a VCN Control Plane is provided that computes all the overlay-to-substrate mappings centrally and publishes them to the NVDs and to the virtual network edge devices such as various gateways such as the DRG, the SGW, the IGW, etc. Firewall rules may also be published using the same mechanism. In certain embodiments, an NVD only gets the mappings that are relevant for that NVD. The data plane functions include functions for the actual routing/forwarding of a packet based upon configuration set up using control plane. A VCN data plane is implemented by encapsulating the customer's network packets before they traverse the substrate network. The encapsulation/decapsulation functionality is implemented on the NVDs. In certain embodiments, an NVD is configured to intercept all network packets in and out of host machines and perform network virtualization functions.

2 FIG. 210 276 268 202 210 212 280 272 206 284 274 208 As indicated above, an NVD executes various virtualization functions including VNICs and VCN VRs. An NVD may execute VNICs associated with the compute instances hosted by one or more host machines connected to the VNIC. For example, as depicted in, NVDexecutes the functionality for VNICthat is associated with compute instancehosted by host machineconnected to NVD. As another example, NVDexecutes VNICthat is associated with bare metal compute instancehosted by host machineand executes VNICthat is associated with compute instancehosted by host machine. A host machine may host compute instances belonging to different VCNs, which belong to different customers, and the NVD connected to the host machine may execute the VNICs (i.e., execute VNICs-relate functionality) corresponding to the compute instances.

2 FIG. 210 277 268 212 283 206 208 An NVD also executes VCN Virtual Routers corresponding to the VCNs of the compute instances. For example, in the embodiment depicted in, NVDexecutes VCN VRcorresponding to the VCN to which compute instancebelongs. NVDexecutes one or more VCN VRscorresponding to one or more VCNs to which compute instances hosted by host machinesandbelong. In certain embodiments, the VCN VR corresponding to that VCN is executed by all the NVDs connected to host machines that host at least one compute instance belonging to that VCN. If a host machine hosts compute instances belonging to different VCNs, an NVD connected to that host machine may execute VCN VRs corresponding to those different VCNs.

2 FIG. 210 286 212 288 In addition to VNICs and VCN VRs, an NVD may execute various software (e.g., daemons) and include one or more hardware components that facilitate the various network virtualization functions performed by the NVD. For purposes of simplicity, these various components are grouped together as “packet processing components” shown in. For example, NVDcomprises packet processing componentsand NVDcomprises packet processing components. For example, the packet processing components for an NVD may include a packet processor that is configured to interact with the NVD's ports and hardware interfaces to monitor all packets received by and communicated using the NVD and store network information. The network information may, for example, include network flow information identifying different network flows handled by the NVD and per flow information (e.g., per flow statistics). In certain embodiments, network flows information may be stored on a per VNIC basis. The packet processor may perform packet-by-packet manipulations as well as implement stateful NAT and L4 firewall (FW). As another example, the packet processing components may include a replication agent that is configured to replicate information stored by the NVD to one or more different replication target stores. As yet another example, the packet processing components may include a logging agent that is configured to perform logging functions for the NVD. The packet processing components may also include software for monitoring the performance and health of the NVD and, also possibly of monitoring the state and health of other components connected to the NVD.

1 FIG. 1 FIG. 2 FIG. 2 FIG. shows the components of an example virtual or overlay network including a VCN, subnets within the VCN, compute instances deployed on subnets, VNICs associated with the compute instances, a VR for a VCN, and a set of gateways configured for the VCN. The overlay components depicted inmay be executed or hosted by one or more of the physical components depicted in. For example, the compute instances in a VCN may be executed or hosted by one or more host machines depicted in. For a compute instance hosted by a host machine, the VNIC associated with that compute instance is typically executed by an NVD connected to that host machine (i.e., the VNIC functionality is provided by the NVD connected to that host machine). The VCN VR function for a VCN is executed by all the NVDs that are connected to host machines hosting or executing the compute instances that are part of that VCN. The gateways associated with a VCN may be executed by one or more different types of NVDs. For example, certain gateways may be executed by smartNICs, while others may be executed by one or more host machines or other implementations of NVDs.

As described above, a compute instance in a customer VCN may communicate with various different endpoints, where the endpoints can be within the same subnet as the source compute instance, in a different subnet but within the same VCN as the source compute instance, or with an endpoint that is outside the VCN of the source compute instance. These communications are facilitated using VNICs associated with the compute instances, the VCN VRs, and the gateways associated with the VCNs.

For communications between two compute instances on the same subnet in a VCN, the communication is facilitated using VNICs associated with the source and destination compute instances. The source and destination compute instances may be hosted by the same host machine or by different host machines. A packet originating from a source compute instance may be forwarded from a host machine hosting the source compute instance to an NVD connected to that host machine. On the NVD, the packet is processed using a packet processing pipeline, which can include execution of the VNIC associated with the source compute instance. Since the destination endpoint for the packet is within the same subnet, execution of the VNIC associated with the source compute instance results in the packet being forwarded to an NVD executing the VNIC associated with the destination compute instance, which then processes and forwards the packet to the destination compute instance. The VNICs associated with the source and destination compute instances may be executed on the same NVD (e.g., when both the source and destination compute instances are hosted by the same host machine) or on different NVDs (e.g., when the source and destination compute instances are hosted by different host machines connected to different NVDs). The VNICs may use routing/forwarding tables stored by the NVD to determine the next hop for the packet.

For a packet to be communicated from a compute instance in a subnet to an endpoint in a different subnet in the same VCN, the packet originating from the source compute instance is communicated from the host machine hosting the source compute instance to the NVD connected to that host machine. On the NVD, the packet is processed using a packet processing pipeline, which can include execution of one or more VNICs, and the VR associated with the VCN. For example, as part of the packet processing pipeline, the NVD executes or invokes functionality corresponding to the VNIC (also referred to as executes the VNIC) associated with source compute instance. The functionality performed by the VNIC may include looking at the VLAN tag on the packet. Since the packet's destination is outside the subnet, the VCN VR functionality is next invoked and executed by the NVD. The VCN VR then routes the packet to the NVD executing the VNIC associated with the destination compute instance. The VNIC associated with the destination compute instance then processes the packet and forwards the packet to the destination compute instance. The VNICs associated with the source and destination compute instances may be executed on the same NVD (e.g., when both the source and destination compute instances are hosted by the same host machine) or on different NVDs (e.g., when the source and destination compute instances are hosted by different host machines connected to different NVDs).

2 FIG. 268 202 210 220 232 210 276 268 276 If the destination for the packet is outside the VCN of the source compute instance, then the packet originating from the source compute instance is communicated from the host machine hosting the source compute instance to the NVD connected to that host machine. The NVD executes the VNIC associated with the source compute instance. Since the destination end point of the packet is outside the VCN, the packet is then processed by the VCN VR for that VCN. The NVD invokes the VCN VR functionality, which may result in the packet being forwarded to an NVD executing the appropriate gateway associated with the VCN. For example, if the destination is an endpoint within the customer's on-premise network, then the packet may be forwarded by the VCN VR to the NVD executing the DRG gateway configured for the VCN. The VCN VR may be executed on the same NVD as the NVD executing the VNIC associated with the source compute instance or by a different NVD. The gateway may be executed by an NVD, which may be a smartNIC, a host machine, or other NVD implementation. The packet is then processed by the gateway and forwarded to a next hop that facilitates communication of the packet to its intended destination endpoint. For example, in the embodiment depicted in, a packet originating from compute instancemay be communicated from host machineto NVDover link(using NIC). On NVD, VNICis invoked since it is the VNIC associated with source compute instance. VNICis configured to examine the encapsulated information in the packet and determine a next hop for forwarding the packet with the goal of facilitating communication of the packet to its intended destination endpoint, and then forward the packet to the determined next hop.

200 200 200 200 218 200 200 200 2 FIG. 2 FIG. A compute instance deployed on a VCN can communicate with various different endpoints. These endpoints may include endpoints that are hosted by CSPIand endpoints outside CSPI. Endpoints hosted by CSPImay include instances in the same VCN or other VCNs, which may be the customer's VCNs, or VCNs not belonging to the customer. Communications between endpoints hosted by CSPImay be performed over physical network. A compute instance may also communicate with endpoints that are not hosted by CSPIor are outside CSPI. Examples of these endpoints include endpoints within a customer's on-premise network or data center, or public endpoints accessible over a public network such as the Internet. Communications with endpoints outside CSPImay be performed over public networks (e.g., the Internet) (not shown in) or private networks (not shown in) using various communication protocols.

200 200 2 FIG. 2 FIG. 2 FIG. The architecture of CSPIdepicted inis merely an example and is not intended to be limiting. Variations, alternatives, and modifications are possible in alternative embodiments. For example, in some implementations, CSPImay have more or fewer systems or components than those shown in, may combine two or more systems, or may have a different configuration or arrangement of systems. The systems, subsystems, and other components depicted inmay be implemented in software (e.g., code, instructions, program) executed by one or more processing units (e.g., processors, cores) of the respective systems, using hardware, or combinations thereof. The software may be stored on a non-transitory storage medium (e.g., on a memory device).

4 FIG. 4 FIG. 4 FIG. 402 404 402 406 408 402 410 412 414 412 406 420 408 422 depicts connectivity between a host machine and an NVD for providing I/O virtualization for supporting multitenancy according to certain embodiments. As depicted in, host machineexecutes a hypervisorthat provides a virtualized environment. Host machineexecutes two virtual machine instances, VM1belonging to customer/tenant #1 and VM2belonging to customer/tenant #2. Host machinecomprises a physical NICthat is connected to an NVDvia link. Each of the compute instances is attached to a VNIC that is executed by NVD. In the embodiment in, VM1is attached to VNIC-VM1and VM2is attached to VNIC-VM2.

4 FIG. 410 416 418 406 416 408 418 402 410 As shown in, NICcomprises two logical NICs, logical NIC Aand logical NIC B. Each virtual machine is attached to and configured to work with its own logical NIC. For example, VM1is attached to logical NIC Aand VM2is attached to logical NIC B. Even though host machinecomprises only one physical NICthat is shared by the multiple tenants, due to the logical NICs, each tenant's virtual machine believes they have their own host machine and NIC.

416 418 406 402 412 414 408 402 412 414 424 402 412 426 424 402 426 420 422 4 FIG. 4 FIG. In certain embodiments, each logical NIC is assigned its own VLAN ID. Thus, a specific VLAN ID is assigned to logical NIC Afor Tenant #1 and a separate VLAN ID is assigned to logical NIC Bfor Tenant #2. When a packet is communicated from VM1, a tag assigned to Tenant #1 is attached to the packet by the hypervisor and the packet is then communicated from host machineto NVDover link. In a similar manner, when a packet is communicated from VM2, a tag assigned to Tenant #2 is attached to the packet by the hypervisor and the packet is then communicated from host machineto NVDover link. Accordingly, a packetcommunicated from host machineto NVDhas an associated tagthat identifies a specific tenant and associated VM. On the NVD, for a packetreceived from host machine, the tagassociated with the packet is used to determine whether the packet is to be processed by VNIC-VM1or by VNIC-VM2. The packet is then processed by the corresponding VNIC. The configuration depicted inenables each tenant's compute instance to believe that they own their own host machine and NIC. The setup depicted inprovides for I/O virtualization for supporting multi-tenancy.

5 FIG. 5 FIG. 5 FIG. 5 FIG. 500 504 500 depicts a simplified block diagram of a physical networkaccording to certain embodiments. The embodiment depicted inis structured as a Clos network. A Clos network is a particular type of network topology designed to provide connection redundancy while maintaining high bisection bandwidth and maximum resource utilization. A Clos network is a type of non-blocking, multistage or multi-tiered switching network, where the number of stages or tiers can be two, three, four, five, etc. The embodiment depicted inis a 3-tiered network comprising tiers 1, 2, and 3. The TOR switchesrepresent Tier-0 switches in the Clos network. One or more NVDs are connected to the TOR switches. Tier-0 switches are also referred to as edge devices of the physical network. The Tier-0 switches are connected to Tier-1 switches, which are also referred to as leaf switches. In the embodiment depicted in, a set of “n” Tier-0 TOR switches are connected to a set of “n” Tier-1 switches and together form a pod. Each Tier-0 switch in a pod is interconnected to all the Tier-1 switches in the pod, but there is no connectivity of switches between pods. In certain implementations, two pods are referred to as a block. Each block is served by or connected to a set of “n” Tier-2 switches (sometimes referred to as spine switches). There can be several blocks in the physical network topology. The Tier-2 switches are in turn connected to “n” Tier-3 switches (sometimes referred to as super-spine switches). Communication of packets over physical networkis typically performed using one or more Layer-3 communication protocols. Typically, all the layers of the physical network, except for the TORs layer are n-ways redundant thus allowing for high availability. Policies may be specified for pods and blocks to control the visibility of switches to each other in the physical network so as to enable scaling of the physical network.

A feature of a Clos network is that the maximum hop count to reach from one Tier-0 switch to another Tier-0 switch (or from an NVD connected to a Tier-0-switch to another NVD connected to a Tier-0 switch) is fixed. For example, in a 3-Tiered Clos network at most seven hops are needed for a packet to reach from one NVD to another NVD, where the source and target NVDs are connected to the leaf tier of the Clos network. Likewise, in a 4-tiered Clos network, at most nine hops are needed for a packet to reach from one NVD to another NVD, where the source and target NVDs are connected to the leaf tier of the Clos network. Thus, a Clos network architecture maintains consistent latency throughout the network, which is important for communication within and between data centers. A Clos topology scales horizontally and is cost effective. The bandwidth/throughput capacity of the network can be easily increased by adding more switches at the various tiers (e.g., more leaf and spine switches) and by increasing the number of links between the switches at adjacent tiers.

1 ocid.<RESOURCE TYPE>.<REALM>.[REGION][.FUTURE USE].<UNIQUE ID>where,ocid1: literal string indicating the version of the CID; Theresource type: The type of resource (for example, instance, volume, VCN, subnet, user, group, and so on);realm: The realm the resource is in. Example values are “c1” for the commercial realm, “c2” for the Government Cloud realm, or “c3” for the Federal Government Cloud realm, etc. Each realm may have its own domain name;region: The region the resource is in. If the region is not applicable to the resource, this part might be blank;future use: Reserved for future use.unique ID: The unique portion of the ID. The format may vary depending on the type of resource or service. In certain embodiments, each resource within CSPI is assigned a unique identifier called a Cloud Identifier (CID). This identifier is included as part of the resource's information and can be used to manage the resource, for example, via a Console or through APIs. An example syntax for a CID is:

6 FIG.A 6 FIG.A depicts an architecture of a hybrid general processing unit (GPU) cluster according to some embodiments. The hybrid GPU cluster includes a plurality of GPU clusters that are communicatively coupled to one another via a hierarchical structure of switches (e.g., a CLOS architecture of switches arranged in a tiered manner). It is noted that the CLOS architecture enables scaling of GPUs to ranges much larger than traditional GPU clusters. The hybrid GPU architecture enables multiple GPU clusters to coexist in a same network fabric-referred to herein as a GPU fabric. In some implementations, at least some of the GPU clusters operate at speeds that are different than operating speeds of some other GPU clusters included in the hybrid GPU architecture. For example, the hybrid GPU cluster may include one or more GPU clusters operating at 100G, and one or more GPU clusters operating at 400G. The hybrid GPU cluster architecture ofis also referred to herein as a GPU supercluster architecture.

600 600 605 625 605 631 625 633 631 619 619 633 629 629 6 FIG.A The GPU supercluster architectureincludes a plurality of blocks that host a plurality of GPU clusters. For instance, as shown in, the GPU supercluster architectureincludes ‘K’ blocks (e.g., block 1,to block K,), where each block is configured to host a particular GPU cluster. A first block (e.g., block 1) hosts a first GPU cluster, whereas a Kth block (i.e., block K) hosts a second GPU cluster. It is noted that each GPU cluster included within a block is hosted on one or more racks. For example, the first GPU clusterincludes a first set of GPUs that are hosted on one or more racks (e.g., rack 1 (A) to rack K (B)). Similarly, the second GPU clusterincludes a second set of GPUs that are hosted on one or more racks (e.g., rack 1 (A) to rack M (B)).

631 631 633 According to some embodiments, the first GPU clusteris a GPU cluster that operates at a first speed (e.g., 100G). More specifically, the first GPU clusterincludes one or more GPUs (i.e., the first set of GPUs), where a network link from the GPU operates at the first speed. In other words, in a host machine a GPU card is paired with a network interface card (NIC), it is the NIC that operates at the first speed. Similarly, the second GPU clusteris a GPU cluster that operates at a second speed (e.g., 400G).

633 Specifically, the second GPU clusterincludes one or more GPUs (i.e., the second set of GPUs), where the second speed is different than the first speed.

1 2 3 605 617 617 625 628 628 605 615 615 625 627 627 601 613 613 621 623 623 6 FIG.A The CLOS architecture includes a tiered or hierarchical structure of switches including a first tier of switches (T), a second tier of switches (T), and a third tier of switches (T). In one implementation, the first tier of switches and the second tier of switches are each included in the blocks of the supercluster architecture. For example, as shown in, block 1includes a plurality of first tier switchesA-B, whereas block Kincludes a plurality of first tier switchesA-B. In a similar manner, block 1includes a plurality of second tier switchesA-B, whereas block Kincludes a plurality of second tier switchesA-B. The network fabric further includes a third tier of switches. In some implementations, the switches in the third tier may be partitioned to form groups of third tier of switches e.g., switches in group labeled(i.e., switchesA toB), and switches in group labeled(i.e., switchesA toB), respectively. It is noted that switches in the third-tier are also referred to herein as upper layer switches. Each group of switches in the third tier of switches communicatively couples the blocks as described below.

613 613 623 623 615 615 627 627 617 617 628 628 631 633 In some implementations, the tiered/hierarchical level of switches are arranged as follows: (i) a Tier 3 (or upper-layer switches) that have ports operating at the second speed e.g., 400G. As such, these switches (e.g., switchesA,B,A, andB) can support 100G, 200G, or 400G switches being attached to it, (ii) a Tier 2 (or mid-level switches e.g., switchesA,B,A, andB) that are configured to support 400G connections either as 4×100 G connections (i.e., multiple 100G connections) or 1× 400G connection (i.e., a single 400G connection); and (iii) a Tier 1 (or bottom-level switches e.g., switchesA,B,A, andB), wherein a type of switch that is to be deployed is selected based on a type of GPU cluster that these switches are expected to be connected to. For example, if one desires to connect a rack of GPUs, where each GPU is operating at 100G speed (e.g., GPUs in cluster 1), then the Tier-1 switch selected is a 100G switch, whereas if one desires to connect a rack of GPUs, where each GPU is operating at 400G speed (e.g., GPUs in cluster), then the Tier-1 switches selected are 400G switches.

As stated previously, the fabric of the GPU supercluster is arranged as a plurality of blocks, where each block supports a GPU cluster operating at a certain speed. The GPU supercluster includes at least a first GPU cluster operating at a first speed and a second GPU cluster that operates at a second speed that is different than the first speed. In each block, the Tier 1 switches are communicatively coupled (at one end) to the cluster of GPUs that are hosted on one or more racks and are coupled (at the other end) to the Tier 2 switches. In turn, the Tier 2 switches communicatively couple the Tier 1 switches to Tier 3 switches. The Tier 3 switches are configured to couple the different blocks together i.e., they communicatively couple the different clusters of GPUs.

6 FIG.A 605 617 617 631 617 605 619 617 619 617 619 617 Referring to, block 1includes K Tier-1 switches (e.g., K=64 switches) e.g., switches labeledA-B, where each Tier-1 switch has M upstream ports (i.e., ports facing Tier-2 switches) and M downstream ports (i.e., ports facing the GPU racks), e.g., M=32 ports. Each upstream and downstream port of these Tier-1 switches operates at a first speed e.g., 100G (as these switches are coupled to the GPU clusterthat operates at the first speed of 100G). The downstream ports of the Tier-1 switches are coupled to the GPU racks. For instance, a particular Tier-1 switch (e.g., switchA) in block 1is coupled to a rack of GPUs (A) whereas switchB is coupled to rackB. The M downstream ports of switchA are communicatively coupled to the rack (A), which includes P GPUs (e.g., P=M/2), where each GPU is connected to the switch via two links (i.e., utilizes two ports of the switchA), thereby providing a pair of 2×100G connections.

617 615 615 615 630 615 615 615 613 1 623 6 FIG.A 6 FIG.A The M upstream ports of switchA (e.g., M=32 ports) are communicatively coupled to M Tier-2 switches (e.g., switchesA,B). It is noted that the Tier-2 switches have a dimension of P downstream ports and P upstream ports (e.g., P=16), where each port operates at a second speed e.g., 400G (i.e., different that the operating speed of the upstream ports of the Teir-1 switches). For example, as shown in, switchA has P=16 downstream ports labeled. In this case, each downstream port of a Tier-2 switch (e.g., switchA) that operates at 400G is split (e.g., optically) into multiple (e.g., four) 100G ports (referred to herein as sub-ports). Thereafter, each sub-port that operates at 100G can be communicatively coupled to a corresponding upstream port of the Tier-1 switch (which operates at 100G). It is appreciated that the splitting of downstream ports of the Tier-2 switches may be accomplished via an optical module connector, which possesses a break out function that has the ability to evenly distribute a large bandwidth at one end into several low speed connections at the other end. The P upstream ports of switchA (Tier-2) that each operate at 400G are communicatively coupled to P=16 Tier-3 switches. For example, as shown in, the P=16 upstream ports of switchA are communicatively coupled to a first Tier-3 switch in each group/upper layer switches e.g., switchA (in upper layer) and switchA (in upper layer P).

625 627 627 625 605 630 615 Turning now to block K, there are included M Tier-2 switches (e.g., switchesA,B), each of which have a dimension of P upstream ports and P downstream ports (e.g., P=M/2). Each of these switches have ports that operate at the second speed. The upstream ports of the Tier-2 switches in block Kare communicatively coupled to the Tier-3 switches in manner similar to that as the coupling of the Tier-2 switches and Tier-3 switches of block 1. However, the P downstream ports of the Tier-2 switches are communicatively coupled to P Tier-1 switches. Specifically, in contrast to the coupling as described above with respect to the downstream portsof the Tier-2 switchA (of block 1), the downstream ports of the Tier-2 switches in block K do not require any form of splitting.

625 633 629 629 628 632 628 650 628 640 629 6 FIG.A 6 FIG.B 6 FIG.B According to some embodiments, the coupling of the downstream ports of the Tier-1 switches in block Kto the GPU clusterhosted on racksA-B can be in one of two forms. In one implementation, and as shown in, for a particular Tier-1 switch (e.g., switchA), the M downstream ports of the switch are connected to M GPUs hosted in a rack. Thus, there is a one-to-one correspondence between a downstream port of the switch and a GPU hosted in a rack. It is noted that such a coupling provides for a single connectionbetween the GPU hosted in a rack and a downstream port of the switchA. In another implementation(as shown in), with an aim to provide more flexibility to a host, a link aggregation technique (e.g., link bonding) is utilized, wherein for instance, a single 400G interface of a port of the switchA is presented as two distinct links (labeled asin) to an application that is executed on a GPU hosted on rackA. Thus, the above described implementations provide for the functionality of presenting to an application executed on a GPU, one of a 1×400G link (i.e., single connection) or 2×200G links (i.e., a bond or multiple connections).

6 6 FIGS.A andB 9 12 FIGS.- 6 6 FIGS.A andB 6 6 FIGS.A andB 6 6 FIGS.A andB Thus, as described above the supercluster architecture(s) ofdeliver ultra-high performance at enhanced scales. The multi-tier CLOS topology provides for a non-blocking network fabric that can scale to tens of thousands of GPUs. It is noted that while a traditional GPU cluster may fit within a few rows e.g., in one room of a datacenter, the large-scale supercluster can span multiple rooms (i.e., data-halls) within a building or even multiple adjoining buildings in a datacenter complex. The cable distance between two GPUs may be longer, which may result in some packets going across these data-halls and incurring slightly higher latency. Techniques are discussed below with reference toto counteract the potential higher latency that may be incurred. Furthermore, it is appreciated that the architectures described above with reference toare merely examples and are not intended to be limiting the scope of the present disclosure. Variations, alternatives, and modifications are possible in alternative embodiments. For example, in some implementations, the architectures may have more or fewer systems or components than those shown in, may combine two or more systems, or may have a different configuration (e.g., switch dimensions, number of tiered layers in the CLOS topology, number of blocks, types (i.e., speeds) of GPU clusters, etc.,) or arrangement of systems. The systems, subsystems, and other components depicted inmay be implemented in software (e.g., code, instructions, program) executed by one or more processing units (e.g., processors, cores) of the respective systems, using hardware, or combinations thereof. The software may be stored on a non-transitory storage medium (e.g., on a memory device).

7 FIG. 7 FIG. 7 FIG. 7 FIG. 7 FIG. 700 illustrates an exemplary flowchartdepicting steps performed in provisioning a request using the hybrid GPU cluster. The processing depicted inmay be implemented in software (e.g., code, instructions, program) executed by one or more processing units (e.g., processors, cores) of the respective systems, hardware, or combinations thereof. The software may be stored on a non-transitory storage medium (e.g., on a memory device). The method presented inand described below is intended to be illustrative and non-limiting. The steps depicted inmay be performed by a control plane of the network fabric. Althoughdepicts the various processing steps occurring in a particular sequence or order, this is not intended to be limiting. In certain alternative embodiments, the steps may be performed in some different order or some steps may also be performed in parallel.

705 705 710 720 The process commences in step, wherein a network fabric is provided, where the network fabric includes a plurality of GPU clusters. Each GPU cluster includes one or more GPUs that are hosted on one or more racks. The plurality of GPU clusters includes at least a first GPU cluster that operates at a first speed and a second GPU cluster that operates at a second speed (that is different from the first speed). In some implementations, the providing of the network fabric of stepmay include sub-steps-as described below.

710 715 720 725 730 6 FIG.A In step, a plurality of blocks are instantiated, where each block includes one or more racks to host GPUs that belong to a particular GPU cluster. It is noted that a single GPU cluster is housed within a block. Thus, a first block may host the first GPU cluster operating at the first speed and a second block may host the second GPU cluster operating at the second speed. In step, a plurality of switches are arranged in a hierarchical manner (i.e., the CLOS architecture). In some implementations, the hierarchical structure of switches may correspond to a three-tiered switch architecture. In this case, switches belonging to tier 1 and 2 may be provided in each block of the network fabric as depicted in. In step, a plurality of groups of upper layer switches may be provided. Note that this layer of switches may correspond to a Tier-3 layer of switches in the CLOS architecture. The Tier-3 layer of switches communicatively couple the different blocks included in the network fabric. In step, a request may be received by the control plane of the network fabric. The request may correspond to a customer's request for execution of a workload. In response to receiving the request, in step, the control plane may allocate one or more GPUs (based on constraints associated with the request) from the plurality of GPU clusters to execute the workload.

8 FIG. 8 FIG. 8 FIG. 800 800 605 625 619 812 814 625 629 822 824 depicts a block diagram of a cloud infrastructureincorporating a CLOS network arrangement of switches, according to certain embodiments. The cloud infrastructureincludes a plurality of blocks e.g., block 1-block K. Each block may include a plurality of racks, wherein each rack hosts a plurality of host machines (also referred to herein as hosts). For sake of simplicity, the blocks depicted inare illustrated to include a single rack. However, it is noted that the blocks may include multiple racks. Block 1 includes rackA that is depicted as including two host machines i.e., Host 1-Aand Host 1-B. Similarly, block Kincludes rackA that is depicted as including two other host machines i.e., Host 2-Aand Host 2-B. It is appreciated that in the illustration of(i.e., each rack including two host machines) is intended to be illustrative and non-limiting. For instance, the cloud infratsructure may include more than two racks, where each rack may include more than two host machines. Moreover, it is noted that each rack is not constraint to have the same number of hosts. Rather, a rack may have a higher or lower number of host machines as compared to the number of host machines included in another rack.

812 813 619 617 812 814 629 627 622 624 617 627 8 FIG. 6 FIG. 8 FIG. Each host machine includes a plurality of graphical processing units (GPUs). For instance, host machine 1-Aincludes N GPUs e.g., GPU 1,. Moreover, it is appreciated that the illustration inof having each host machine including the same number of GPUs, i.e., N GPUs, is intended to be illustrative and non-limiting i.e., each host machine can include a different number of GPUs. Each rack is associated with a Tier-1 switch (also referred to herein as a top of rack (TOR) switch) that is communicatively coupled with the GPUs hosted on the host machines within the rack. For example, rack 1A is associated with a TOR switchA that is communicatively coupled to host machines Host 1-A,and Host 1-B,, whereas rack 2A is associated with a TOR switchA that is communicatively coupled to host machines Host 2-A,and Host 2-K,. It is appreciated that the TOR switches depicted in(i.e., switchesA, andA), each include N ports that are used to communicatively couple the TOR switch to the N GPUs hosted on each host machine included in the corresponding rack. The coupling of TOR switches to the GPUs as depicted inis intended to be illustrative and non-limiting. For instance, in some embodiments, the TOR switch may have a plurality of ports, each of which corresponds to a GPU on each host machine i.e., a GPU on a host machine may be connected to a unique port of the TOR via a communication link.

617 615 615 627 623 623 613 613 623 623 6 FIG.A 8 FIG. 8 FIG. The TOR switches associated with each rack are communicatively coupled to one or more Tier-2 switches in each block. For example, switchA is communicatively coupled to Tier-2 switchesA-B, whereas switchA is communicatively coupled to switchesA-B. Similar to the configuration of, the Tier-2 switches are communicatively coupled to the upper layer switchesA-B andA-B as shown. Information transmitted from a particular Tier-1 switch to a Tier-2 switch (or from a Tier-2 switch to a Tier-3 switch) is referred to herein as communication conducted via an uplink, whereas information transmitted from Tier-1 switch to a host machine (or from a Tier-3 switch to a Tier-2 switch) is referred to herein as communication conducted via a downlink. According to some embodiments, the tiered switches ofform a CLOS network arrangement (e.g., a multi-stage switching network), where each Tier-1 switch may be considered as forming a ‘leaf’ node in the CLOS network.

According to some embodiments, the GPUs included in the host machines execute tasks related to machine learning. In such a setting, a single task may be performed/spread across a large number of GPUs that could be spread across multiple host machines, across multiple racks, and/or across different blocks. Since all these GPUs are working on the same task (i.e., a workload), they all need to communicate with each other in a time synchronized manner. Furthermore, at any given time, the GPUs are either in one of a compute mode or a communication mode i.e., GPUs talk to one another at roughly the same time instant. The speed of the workload is determined by the speed of the slowest GPU.

Typically, to route packets from a source GPU to a destination GPU, equal cost multipath (ECMP) routing is utilized. In ECMP routing, when there are multiple equal cost paths available for routing traffic from a sender to a receiver, a selection technique is used to select a particular path. Accordingly, at a network device (e.g., a TOR switch) receiving the traffic, a selection algorithm is used to select an outgoing link to be used for forwarding the traffic from the network device to a subsequent device. This outgoing link selection occurs at each network device in the path from the sender to the receiver. Hash-based selection is a widely used ECMP selection technique, where the hash may be based, for example, on a 4-tuple of a packet (e.g., source port, destination port, source IP, destination IP).

ECMP routing is a flow aware routing technique, where each flow (i.e., a stream of data packets) is hashed to the same path for the duration of the flow. Thus, packets in a flow are forwarded from a network device using a particular outgoing port/link. This is typically done in order to ensure that packets in a flow arrive in order i.e., no re-ordering of packets is required. However, ECMP routing is bandwidth (or throughput) unaware. In other words, the switches perform statistical flow-aware (throughput unaware) ECMP load balancing of flows on parallel links.

8 FIG. 8 FIG. 841 812 617 843 814 617 617 850 617 615 In standard ECMP routing (i.e., only flow aware routing), a problem is that flows received by a network device over two separate incoming links may get hashed to the same outgoing link, thereby resulting in a flow collision. For instance, consider a situation where the two flows are coming in over two separate incoming 100G links, and each of the flows gets hashed to the same 100G outgoing link. Such a situation results in a congestion (i.e., flow collision) and results in packets being dropped, since the incoming bandwidth is 200G, but outgoing bandwidth is 100G. As shown in, there are two flows: flow 1which is directed from a first GPU of the host machine Host 1-A,to the switchA, and flow 2, which is directed from another GPU on the host machine Host 1-B,to the switchA. Note that the two flows are directed to the switch on separate links. For sake of illustration, it is assumed that the links depicted inhave a same capacity (i.e., bandwidth) of 100G. In the case when the switchA performs ECMP routing algorithm, it is possible that the two flows get hashed to use the same outgoing link of the switch e.g., linkthat connects the switchA to a higher tier switch e.g., switchA. In this case, there is a collision between the two flows (represented by ‘X’ mark), which results in packets being dropped.

Such a collision scenario is generally problematic for all types of traffic irrespective of the protocol. For example, TCP is intelligent in that when a packet gets dropped and the sender does not get an acknowledgment for that dropped packet, the packet is re-transmitted. However, the situation is worsened for remote direct memory access (RDMA) type traffic. RDMA networks do not use TCP for a variety of reasons (e.g., TCP does not have a high performance). RDMA networks use protocols such as RDMA over Infiniband or RDMA over converged Ethernet (RoCE). In ROCE, there is a congestion control algorithm, wherein when a sender identifies the occurrence of a congestion or dropped packets, the sender slows down the transmission of packets. For a dropped packet, not only the dropped packets, but also several packets around the dropped packet are retransmitted that further eats away the available bandwidth and results in poor performance.

6 FIG.A The flow collision issue is a critical problem for supercluster GPU architecture of, due to the stringent time synchronization requirements. For example, as stated before, GPUs may execute a machine learning task (i.e., a workload) where all GPUs communicate with each other in a time synchronized manner. For machine learning tasks, and other types of tasks, a logical topology is constructed (e.g., a ring topology, a tree topology, etc.) for the host machines to enable communications between the GPUs. GPUs connect with each other using the logical topology which may be multilevel or multi-dimensional. In some implementations, in order to execute a workload, an application constructs a virtual (or logical) topology to interconnect the GPUs. Typically, such an application is unaware of the underlying physical topology of the host machines and thus attempts to construct the logical topology in a random (i.e., arbitrary) manner. Such randomly constructed logical topologies result in GPU host machines exchanging traffic without regard for which other GPU host(s) are in their local network neighborhood. As such, the likelihood for traffic congestion is increased which results in poor GPU throughput. For example, consider the case where a pair of host machines is required to execute a certain machine learning task. In this case, if a random selection of the pair of host machines is performed, where one of the host machines resides in a first local neighborhood (e.g., a first rack) and the other host machine resides in another local neighborhood (different than the first local neighborhood) e.g., a second rack, then the execution of the machine learning task would incur a certain amount of latency (e.g., delay incurred in communication between the first host machine and the second host machine), as well as may increase the likelihood of traffic congestion. In contrast, if the pair of host machines selected for executing the machine learning task reside in the same local neighborhood (e.g., reside in the same rack, or a same block), it is appreciated that communication between the host machines incurs minimal latency, as well as improves the likelihood of avoiding traffic congestion.

Described below are techniques to overcome the above described problems. Specifically, the techniques described herein utilize hierarchical locality information of the GPUs in the process of constructing the logical topology and thereby avoids needless traffic congestion. Moreover, embodiments of the present disclosure provide for customers to reduce their application to service latency by “placing” their workload(s) on nearby host machines. Further, customers may use the locality information and place their workloads in ways to get higher anti-affinity and thus gain higher resiliency by reducing shared fate of the resources.

8 FIG. 9 10 FIGS.and 812 814 619 617 According to some embodiments, host machines are unaware of the physical topology of the network i.e., a particular host machine is unaware of the physical location/position of other host machines in the network. For example, referring to, host machine 1-Ais unaware that host machine 1-Bis in fact included in the same rack (i.e., rackA) and positioned behind the same TOR switch i.e., switchA. However, a network control plane is aware of the overall physical topology of the host machines. In one implementation, the network control plane publishes such locality information (e.g., a hierarchical locality information identifying at least a rack comprising the host machine, a block hosting the rack, etc.,) to the host machines in order to achieve traffic locality and avoid needless traffic congestion. Doing so has a significant impact on the performance of GPU workloads as illustrated below with reference to.

By some embodiments, the network control plane utilizes an instance metadata service (IMDS) to publish (and store) metadata information (e.g., hierarchical locality information) to a host machine. Such metadata information may be published to the host machine(s) via a network virtualization device (NVD) associated with the host machine(s). It is appreciated that hierarchical locality information may include metadata indicating a rack identifier of the rack comprising the host machine as well as a block identifier of the block hosting the rack. It is appreciated that each of the host machines may query the IMDS to obtain the metadata information associated with the host machine. As is described below, the published locality information is utilized to construct optimal logical topologies to achieve higher GPU workload throughputs.

9 FIG. 9 FIG. 9 FIG. 9 FIG. 9 FIG. 901 903 905 907 909 911 913 915 901 903 905 907 909 911 913 915 Turning to, there is depicted a logical topology that is constructed without considering locality information of the host machines, according to certain embodiments. The logical topology depicted incorresponds to a scenario of having eight host machines i.e., Host machine 1-A, Host machine 1-B, Host machine 2-A, Host machine 2-B, Host machine 3-A, Host machine 3-B, Host machine 4-A, and Host machine 4-B. As shown in, it is noted that Host machines 1-Aand 1-Bare located in the same rack i.e., positioned behind a same TOR switch. Similarly, the pair of host machines: (Host machines 2-Aand 2-B), (Host machines 3-Aand 3-B), and (Host machines 4-Aand 4-B) are respectively included in other racks, respectively. This is represented inas ‘TOR local traffic’. Further, it is noted that host machines 1-A, 1-B, 2-A, 2-B, 3-A, and 3-B are included in the same block (i.e., different racks in the same block), whereas host machines 4-A and 4-B are located in another block. This is represented inas ‘Block local traffic’.

9 FIG. 9 FIG. 941 942 943 944 945 946 947 948 The logical topology depicted inis a ring topology that is constructed without hierarchical locality information i.e., the ring topology is constructed in a random (arbitrary) manner. As shown in, the ring is constructed in a manner such that Host 1-A is directly connected to Host 4-B via the links labeled. Further, Host 4-B is connected to Host 3-B via the links labeled, Host 3-B is connected to Host 4-A via links labeled, Host 4-A is connected to Host 3-A via links labeled, Host 3-A is connected to Host 2-B via links labeled, Host 2-B is connected to Host 2-A via links labeled, Host 2-A is connected to Host 1-B via links labeled, and Host 1-B is connected to Host 1-A via links labeled.

9 FIG. 9 FIG. 913 915 942 943 930 930 The logical topology constructed in the manner as shown inis prone to network flow collisions occurring due to ECMP traffic distribution. It is noted that although Host 4-Aand Host 4-Bare positioned behind the same TOR switch i.e., included in the same rack, the traffic originating from Host 4-B and destined for Host 4-A traverses the following route: traffic is first routed from Host 4-B to Host 3-B (i.e., via the virtual links), and then from Host 3-B to Host 4-A (i.e., via virtual links). Thus, traffic intended for a destination host (e.g., Host 4-A) that is positioned in the same rack as the origination host (i.e., Host 4-B) is unnecessarily routed to a host machine (i.e., Host 3-B) that not only lies outside the rack but is located in a completely different block (as compared to the source and destination host machines). In other words, traffic which could have been routed locally within the blockis routed to a host machine outside the block, only to be re-routed back into block. This occurs due to the arbitrarily constructed logical topology of, which leads to increased likelihood of flow collisions, which in turn reduces the throughput of GPU workloads (e.g., higher latency, jitter loss, etc.).

10 FIG. 10 FIG. 9 FIG. 10 FIG. 10 FIG. 10 FIG. 1041 1042 1043 1044 1045 1046 1047 1048 Turning now to, there is depicted another logical topology that is constructed considering hierarchical locality information of the host machines, according to certain embodiments. The logical topology depicted incorresponds to the same eight host machines as those depicted in. The logical topology depicted inis a ring topology that is constructed utilizing hierarchical locality information i.e., the ring topology is constructed based on hierarchical locality information obtained, for example, from IMDS. By some embodiments, the logical topology may be constructed by a configuration host machine which may be one of the host machines depicted in. As shown in, the ring is constructed in a manner such that: Host 1-A is directly connected to Host 4-B via the links labeled. Further, Host 4-B is connected to Host 4-A via the links labeled, Host 4-A is connected to Host 3-B via links labeled, Host 3-B is connected to Host 3-A via links labeled, Host 3-A is connected to Host 2-B via links labeled, Host 2-B is connected to Host 2-A via links labeled, Host 2-A is connected to Host 1-B via links labeled, and Host 1-B is connected to Host 1-A via links labeled.

10 FIG. 9 FIG. 9 FIG. 11 FIG. 9 FIG. 10 FIG. 1042 1100 1105 1102 1105 1102 1105 1102 1107 1104 1102 1102 1102 920 1104 930 The logical topology depicted inavoids traffic between two host machines that are in the same rack (i.e., positioned behind the same TOR switch) from being routed unnecessarily outside the rack and/or block. For instance, considering the same example of, where Host 4-B intends to send traffic to Host 4-A, the traffic can be routed (over a single hop in the virtual layer) via the links. This is in contrast to the situation depicted in, where traffic was routed outside the block (i.e., to Host 3-B) and then re-routed back to the block (i.e., to Host 4-A).depicts a physical topologyof the eight nodes considered the above examples ofand. Specifically, Host 1-A and Host 1-B are depicted to be included in the same rackA (connected by Tier-1 switchA), Host 2-A and Host 2-B are depicted to be included in the same rackB (connected by Tier-1 switchB), Host 3-A and Host 3-B are depicted to be included in the same rackC (connected by Tier-1 switchC), and Host 4-A and Host 4-B are depicted to be included in the same rackA (connected by Tier-1 switchA). It is noted that the Tier-1 switchesA,B, andC are located in the same block, whereas the Tier-1 switchA is located in another block. In this manner constructing the logical topology based on hierarchical locality information leads to a reduced likelihood of flow collisions, which increases the throughput of GPU workloads.

12 FIG. 12 FIG. 12 FIG. 12 FIG. 1200 illustrates an exemplary flowchartdepicting steps performed in provisioning a request using hierarchical locality information, according to certain embodiments. The processing depicted inmay be implemented in software (e.g., code, instructions, program) executed by one or more processing units (e.g., processors, cores) of the respective systems, hardware, or combinations thereof. The software may be stored on a non-transitory storage medium (e.g., on a memory device). The method presented inand described below is intended to be illustrative and non-limiting. Althoughdepicts the various processing steps occurring in a particular sequence or order, this is not intended to be limiting. In certain alternative embodiments, the steps may be performed in some different order or some steps may also be performed in parallel.

1205 The process commences in step, where for each host machine of a plurality of host machines (e.g., host machines included in a GPU cluster) hierarchical locality information for the host machine is stored. Hierarchical locality information for a host machine includes information identifying for instance, a rack comprising the host machine, a block in which the rack is disposed, etc. By some embodiments, the instance metadata service may be utilized to store the hierarchical locality information in the host machine via a network virtualization device (NVD) associated with the host machine. It is noted that hierarchical locality information may correspond to information that indicates for example, an identifier of a rack (i.e., rack ID) which includes the host machine, an identifier of a TOR switch associated with the rack, a block identifier (i.e., block ID) of the block in which the rack is located etc.

1210 1215 In step, a control plane receives a request (e.g., from a customer) requesting execution of a workload. Note that a workload corresponds to one or more processes that are to be executed using the GPUs associated with the host machines. The process then moves to step, where one or more host machines from the plurality of host machines are identified as being available for executing the workload. The identification of available host machines may be performed in several ways. For instance, by one embodiment, the control plane may maintain a current load (i.e., processing workload) handled by a host machine. Based on a capacity of each host machine and the amount of current load handled by the host machine, the control plane may select one or more host machines that are available for executing the workload of the customer. Additionally, by another embodiment, the control plane may pre-allocate a certain number of host machines per customer. Further, the available host machines may be determined from this certain number of host machines.

1210 According to some embodiments, the request received in stepmay include one or more constraints. For instance, the request can include a first constraint associated with a latency threshold i.e., the customer may desire the workload to be executed by having the latency be lower than a predetermined threshold value. A second constraint may correspond to an anti-affinity constraint. Such a constraint corresponds to the customer desiring to have a certain degree of availability of the host machines i.e., at least some of the host machines selected for executing the workload need to be positioned in different racks and/or different blocks. Such a constraint is typically incorporated by the customer to address failure of rack issues. Additionally, the customer's request may include constraints directed to the type of GPUs required to execute the workload. For instance, the request may indicate that the customer desires a first number of GPUs that operate at a first speed (e.g., 100G) and a second number of GPUs that operate at a second speed (e.g., 400G). Such constraints may be considered by the control plane in allocating/identifying the certain number of host machines for the customer.

1220 1215 1225 1230 1240 10 FIG. The process then moves to step, where hierarchical locality information for each of the one or more host machines identified in stepis obtained. It is noted that the locality information (of each host machine) may be stored, e.g., by the instance metadata service in the corresponding host machine. In step, the process identifies linkage information of the one or more host machines. It is appreciated that the linkage information of the one or more host machines corresponds to a logical topology (e.g., logical topology as depicted in) formed by the one or more host machines. Thereafter, the process moves to step, where the hierarchical locality information and the linkage information of the one or more host machines is provided in response to the request from the customer. According to some embodiments, the customer upon obtaining the hierarchical locality information and linkage information may select a subset of the one or more host machines for executing the workload (step). It is noted that the selection of the host machines may be performed based on one or more constraints associated with the workload.

As stated previously, ECMP routing is a flow aware routing technique, where each flow (i.e., a stream of data packets) is hashed to a particular path for the duration of the flow. Thus, packets in a flow are forwarded from a network device using a particular outgoing port/link. This is typically done in order to ensure that packets in a flow arrive in order i.e., no re-ordering of packets is required. However, ECMP routing is bandwidth (or throughput) unaware. In other words, the switches perform statistical flow-aware (throughput unaware) ECMP load balancing of flows on parallel links. In standard ECMP routing (i.e., only flow aware routing), a problem is that flows received by a network device over two separate incoming links may get hashed to the same outgoing link, thereby resulting in a flow collision.

Described below is a routing technique (referred to herein as a GPU based routing policy mechanism or a GPU-based traffic routing mechanism) to overcome the above described flow collision problem. It is appreciated that the flow collision problem affects traffic from CPUs and GPUs. However, the flow collision issue is a much bigger problem for GPUs due to the stringent time synchronization requirements. Furthermore, it is to be appreciated that the standard ECMP routing mechanism will incur the flow collisions scenarios irrespective of whether the network is over or under subscribed due to its inherent property of routing information in a statistical bandwidth unaware manner.

13 FIG. 13 FIG. 8 FIG. 13 FIG. 812 822 814 824 Turning now to, there is depicted a GPU based policy routing mechanism implemented in the hybrid GPU cluster, according to certain embodiments. For sake of convenience and illustration, the architecture depicted inis the same architecture as that depicted in. According to some embodiments, data packets from a sender to a receiver are routed in the network fabric on a hop-by-hop basis. A routing policy is configured at each network device that ties an incoming port-link (of the network device) to an outgoing port-link (of the network device). The network device could be any one of the switches included in the hierarchical structure of switches i.e., Tier-1, 2, or 3. Referring to, there are depicted two flows: flow 1 from GPU 1 on host machinewhose intended destination is GPU 1 on host machine, and flow 2 from GPU N on host machinewhose intended destination is GPU N on host machine. In one implementation, all the network devices (i.e., switches included in the network fabric) are configured to tie (or match) an incoming port-link to an outgoing port-link. A matching of the incoming port-links to outgoing port-links is maintained (e.g., in a policy table) at each network device.

13 FIG. 8 FIG. 13 FIG. 617 841 850 615 850 851 613 613 851 852 623 623 627 853 854 Referring to, it can be observed that with regard to flow 1 (i.e., flow depicted by solid lines), that when the first tier switch (A) receives a packet on link, the first tier switch is configured to forward the received packet on an outgoing link. Similarly, when a second tier switch (A) receives the packet via link, it is configured to forward the packet on outgoing linkto a Tier-3 switch (A). In turn, the Tier-3 switch (A) is configured to forward the packet received on linkto an outgoing link, in order to transmit the packet to a Tier-2 switchA (that is included in another block). SwitchA in turn forwards the packet to switchA on its outgoing link, which in turn forwards the packet on outgoing linkto be delivered to its intended destination. It is noted that the route for flow 2 (i.e., flow depicted by dashed lines) is forwarded by the intermediate network devices in a manner similar to that describe above (with reference to flow 1) to be delivered to its intended destination. It is noted that in contrast to the scenario depicted in(which utilizes ECMP routing), the scenario depicted inavoids route collisions.

14 FIG. Thus, in this manner, in one implementation of the GPU policy based routing mechanism, each network device in the network fabric ofis configured to tie an incoming port/link to an outgoing port/link in order to avoid collisions. It is appreciated that at each network device within the cloud infrastructure, there is a 1-1 correspondence between an incoming port-link and an outgoing port-link i.e., a mapping between the incoming port-link and an outgoing port-link is performed independent of the flows and/or the protocols executed by the flows. Furthermore, in the event that an outgoing link of a particular network device fails, according to some embodiments, the network device is configured to switch its routing policy from the GPU policy based routing to a standard ECMP routing to obtain a new available output link (from various available output links) and send the flow down that new output link. It is noted that in this case, one may incur flow collision resulting in congestion.

14 FIG. 14 FIG. 14 FIG. 14 FIG. 1400 illustrates a flowchartdepicting steps performed by a network device in routing a packet, according to certain embodiments. The processing depicted inmay be implemented in software (e.g., code, instructions, program) executed by one or more processing units (e.g., processors, cores) of the respective systems, hardware, or combinations thereof. The software may be stored on a non-transitory storage medium (e.g., on a memory device). The method presented inand described below is intended to be illustrative and non-limiting. Althoughdepicts the various processing steps occurring in a particular sequence or order, this is not intended to be limiting. In certain alternative embodiments, the steps may be performed in some different order or some steps may also be performed in parallel.

1405 1410 The process commences in step, where a plurality of GPU clusters that are communicatively coupled to one another via a plurality of network devices (e.g., switches) arranged in a hierarchical manner is provided in a network fabric. It is appreciated that a first GPU cluster of the plurality of GPU clusters operates at a first speed (e.g., 100G), whereas a second GPU cluster of the plurality of GPU clusters operates at a second speed (e.g., 400G) that is different than the first speed. The process in stepexecutes a pre-configuration step, where a routing policy is configured for each network device included in the network fabric. Note that the routing policy corresponds to mapping an incoming port-link to an outgoing port-link of the network device.

1415 1420 1425 1410 In step, a network device (e.g., a first network device) receives a data packet transmitted by a graphical processing unit (GPU) of a host machine. In step, the network device determines an incoming port/link that the packet was received on. In step, the network device identifies an outgoing port/link corresponding to the incoming port/link (on which the packet was received) based on a policy routing information i.e., the routing information pre-configured in step. According to some embodiments, the policy routing information corresponds to a pre-configured GPU routing table for the network device that ties each incoming port-link of the network device to a unique outgoing link-port of the network device.

1430 1435 1450 The process then moves to step, where a query is performed to determine whether the outgoing port-link is in a functioning state e.g., the outgoing link is active. If the response to the query is affirmative (i.e., the link is active), then the process moves to step, else if the response to the query is negative (i.e., the link is in a failed state/inactive state), then the process moves to step.

1435 1425 1440 1460 1440 1445 1420 1425 1430 1435 1440 In step, the network device utilizes the outgoing port-link (identified in step) to forward the received data packet to another network device. Further, the process in stepexecutes another query to determine whether the packet has reached its intended destination. If the response to the query if affirmative, the process simply terminates (step). Else, if the response to the query in stepis negative, the process moves to step, where the next network device (i.e., the next-hop network device on the path from the source host machine to the destination host machine) processes the packet. Specifically, the next network device repeats steps,,,, and.

1430 1450 1455 1450 1440 If the response to the query of stepwas negative, then in step, the network device obtains flow information of the data packet e.g., the flow information may correspond to a 4-tuple associated with the packet (i.e., source port, destination port, source IP address, destination IP address). Based on the obtained flow information, the network device utilizes ECMP routing to identify a new outgoing port-link i.e., an available outgoing port-link. The process then moves to step, where the network device utilizes the newly obtained outgoing port-link (in step) to forward the data packet. Thereafter, the process loops back to stepto repeat the process until the packet is delivered to its intended destination.

13 FIG. 617 627 615 615 623 623 According to some embodiments of the present disclosure, in another implementation of the GPU based policy routing framework, only a subset of network devices in the network fabric are configured to tie an incoming port/link to an outgoing port/link. In this implementation, the subset of network devices that implement the GPU based policy routing mechanism correspond to switches included in the Tier-1 and Tier-2 levels of the hierarchical levels of switches. For example, referring to, switchesA,A (included in Tier-1) and switchesA,B,A,B (included in Tier-2) implement the policy based routing. In this implementation, the switches in the Tier-1 and Tier-2 levels tie an incoming uplink/port to an outgoing uplink/port of the switch. It is noted that in this implementation, the switches included in the Tier-3 level do not implement the GPU policy based routing. Rather, the switches in this level may implement standard routing protocols (e.g., ECMP routing) to route the traffic. Additionally, it is appreciated that in both implementations of the GPU policy based routing, when a particular switch receives a packet that is to be forwarded, the switch determines whether a next hop of the packet is on one of the downlinks of the switch. If so, in some implementations, the packet is transmitted without policy based routing i.e., forwarded using standard routing protocols. If the packet is to be forwarded on an uplink then the switch may utilize policy based routing—i.e., dependent on the tier in which the switch is included.

6 6 FIG.A orB According to some embodiments, the deployment of the GPU supercluster architecture ofposes challenges with respect to the management of a global address space (e.g., MAC addresses of each GPU included in the plurality of clusters of GPUs). Specifically, with the deployment of a large scale GPU cluster, each Tier-1 switch is required to manage and maintain (i.e., store) a MAC address table (e.g., forwarding table) including addresses of each GPU included in the cluster. Doing so, may result in an overflow of the forwarding tables of the switches. There are two problems associated with this scenario:-switches are associated with a control plane (i.e., where BGP and other routing protocols reside), and a data plane (i.e., where forwarding tables reside). The problem of maintaining an efficient address space exists in both the control plane and the data plane.

6 6 FIG.A orB It is appreciated that forwarding tables are required to store MAC addresses (i.e., for overlay customer networks) as well as IP addresses (i.e., for underlay physical networks). As storage space in forwarding tables is limited, the problem is exacerbated in the scenario of deploying the GPU supercluster architecture of. In other words, the problem presented due to the limited storage space of the forwarding tables is that of how does one limit the size of the forwarding table so that one can scale the network without having to scale the size of the forwarding table. Described below are techniques that can be utilized in both, the control plane and the data plane, respectively, for providing mechanisms to efficiently manage the storage space of the forwarding tables.

15 FIG.A 15 FIG.A 15 FIG.A 1501 1521 1501 1503 1503 1521 1523 1523 depicts an architecture of a hybrid GPU cluster illustrating placement of route reflectors according to some embodiments. For sake of illustration,depicts the architecture as including two blocks i.e., a first blockand a second block. Each of the first block and the second block include a hierarchical structure of switches deployed therein. For instance, as shown in, the first blockincludes a first tier of switches (i.e., Tier-1 switches) labeledA and a second tier of switches (i.e., Tier-2 switches) labeledB. The second blockincludes a first tier of switches labeledA and a second tier of switches labeledB.

6 FIG.A 15 FIG.A 6 FIG.A 1503 1523 1503 1523 Similar to the architecture of, the GPU supercluster architecture ofincludes a third tier of switches (i.e., Tier-3 switches) labeledC andC, respectively. It is appreciated that a plurality of switches included in the third tier of switches may be partitioned into a plurality of groups of third tier of switches (e.g., groupC,C, respectively). Furthermore, it is noted that similar to the architecture of, the first tier of switches are communicatively coupled at one end to the plurality of GPU clusters and at another end to the second tier of switches. In turn, the second tier of switches communicatively couple the first tier of switches to the third tier of switches, where the third tier of switches communicatively couple the different blocks included in the GPU supercluster architecture.

According to some embodiments, one or more switches are selected from the third tier of switches to form a set of target switches. Such target switches are referred to herein as route reflectors. It is noted that the selection of the set of target switches may be performed (in some implementations) in a random manner. In other implementations, a route reflector may be selected from each group of the plurality of groups of third tier switches. For example, a first switch included in each group of the third tier switches may be designated to perform the functions of the route reflector as described below. According to some embodiments, a total number of target switches included in the set of target switches is in a range from 4 to 16.

1503 1523 1503 1523 By some embodiments, each switch included in the first tier of switches (A,A) forms a peering connection (e.g., BGP peering) with each of the one or more target switches i.e., route reflectors included in the third tier of switches (C,C). The route reflectors are configured to reduce address information (e.g., MAC addresses) that is maintained in forwarding tables by the Tier-1 switches as described below. It is appreciated that when a particular Tier-1 switch receives a packet from a GPU (i.e., a GPU coupled to the particular Tier-1 switch), the Tier-1 switch may transmit address information of the GPU to each target switch via the peering connection. In this manner, each target switch that is included in the Tier-3 layer of switches, receives address information of each GPU included in the plurality of GPU clusters.

Upon receiving the address information of each GPU included in the plurality of GPU clusters, each target switch processes the received address information to generate a plurality of sets of address information. For instance, according to one embodiment, a particular target switch may filter the received address information to generate one or more sets of address information based on certain conditions. In one instance, the target switch may filter the received address information of GPUs based on a VLAN of a customer that a GPU belongs to. In other words, the sets of address information generated by the target switch corresponds to grouping together GPUs that are associated with a customer. Further, each target switch may advertise/transmit the generated one or more sets of address information to each switch included in the Tier-1 layer of switches. A particular Tier-1 switch, in turn, stores (in the forwarding table) only a subset of the received one or more sets of address information in accordance with the condition. For instance, if the particular Tier-1 switch is associated with a particular customer VLAN, then the particular Tier-1 switch may only store MAC addresses of GPUs that belong to the same customer VLAN. In this manner, the particular Tier-switch may ignore (e.g., discard) the other sets of received address information that correspond to GPUs associated with other customer VLANs. It is appreciated that the target switches may utilize other conditions for generating the one or more sets of address information. For example, the target switches may filter address information of the GPUs based on a type of GPU (i.e., blocks of GPUs operating at different speeds). In this manner, the route reflectors reduce the MAC address space in the forwarding tables in the control plane.

According to some embodiments, techniques may be utilized at the data plane layer to achieve further reduction in the number of MAC addresses maintained in the forwarding table. For example, by one technique, the switches in the Tier-1 level may be configured to the switch is further configured to purge an entry from the address table based on a timer associated with the entry. Further, a least recently used mechanism may be employed, wherein based on a usage (e.g., least used) of a particular entry, the entry may be purged from the forwarding table. Yet another approach may include summarizing the entries in an IP table (corresponding to addresses of underlay physical network components), thereby providing more storage space for MAC entries in the forwarding table. Thus, by techniques described above, embodiments of the present disclosure limit the size of the forwarding table, in order to scale the GPU cluster network without having to compromise on scaling the size of the forwarding table.

15 FIG.B 15 FIG.B 15 FIG.B 15 FIG.B 1550 illustrates a flowchartdepicting steps performed by route reflectors in managing a size of an address table that is stored by switches, according to certain embodiments. The processing depicted inmay be implemented in software (e.g., code, instructions, program) executed by one or more processing units (e.g., processors, cores) of the respective systems, hardware, or combinations thereof. The software may be stored on a non-transitory storage medium (e.g., on a memory device). The method presented inand described below is intended to be illustrative and non-limiting. Althoughdepicts the various processing steps occurring in a particular sequence or order, this is not intended to be limiting. In certain alternative embodiments, the steps may be performed in some different order or some steps may also be performed in parallel.

1555 The process commences in step, where a plurality of GPU clusters that are communicatively coupled to one another via a plurality of network devices (e.g., switches) arranged in a hierarchical manner is provided in a network fabric. It is appreciated that a first GPU cluster of the plurality of GPU clusters operates at a first speed (e.g., 100G), whereas a second GPU cluster of the plurality of GPU clusters operates at a second speed (e.g., 400G) that is different than the first speed. The hierarchical structure of switches includes at least a Tier-1 level of switches, Tier-2 level of switches, and a Tier-3 level of switches.

1560 1565 In step, the process selects one or more switches from the Tier-3 layer of switches to form a set of target switches (i.e., route reflectors). In step, each target switch included in the set of target switches receives address information (e.g., MAC addresses) of each GPU included in the plurality of GPU clusters. As described previously, each Tier-1 switch is configured to establish a peering connection (e.g., BGP connection) with each of the target switches included in the Tier-3 layer of switches. By some embodiments, address information of the GPUs may be transmitted to the target switches (e.g., by the Tier-1 switches upon receiving a packet from a GPU) via the peered connection.

1570 1575 The process thereafter moves to step, where each target switch generates a plurality of sets of address information. By some embodiments, such sets of address information may be generated by filtering/grouping the received address information of the GPUs based on certain conditions. For example, as stated previously, a target switch may filter the received address information of GPUs based on a VLAN of a customer that a GPU belongs to. In other words, the sets of address information generated by the target switch corresponds to grouping together GPUs that are associated with a customer. In step, the target switch advertises/transmits the plurality of sets of address information to each switch included in the Tier-1 level of switches. A switch included in the Tier-1 level of switches, upon receiving the sets of address information stores a subset of the plurality of sets of address information in accordance with the condition in order to conserve the storage space of forwarding tables.

As noted above, infrastructure as a service (IaaS) is one particular type of cloud computing. IaaS can be configured to provide virtualized computing resources over a public network (e.g., the Internet). In an IaaS model, a cloud computing provider can host the infrastructure components (e.g., servers, storage devices, network nodes (e.g., hardware), deployment software, platform virtualization (e.g., a hypervisor layer), or the like). In some cases, an IaaS provider may also supply a variety of services to accompany those infrastructure components (e.g., billing, monitoring, logging, security, load balancing and clustering, etc.). Thus, as these services may be policy-driven, IaaS users may be able to implement policies to drive load balancing to maintain application availability and performance.

In some instances, IaaS customers may access resources and services through a wide area network (WAN), such as the Internet, and can use the cloud provider's services to install the remaining elements of an application stack. For example, the user can log in to the IaaS platform to create virtual machines (VMs), install operating systems (OSs) on each VM, deploy middleware such as databases, create storage buckets for workloads and backups, and even install enterprise software into that VM. Customers can then use the provider's services to perform various functions, including balancing network traffic, troubleshooting application issues, monitoring performance, managing disaster recovery, etc.

In most cases, a cloud computing model will require the participation of a cloud provider. The cloud provider may, but need not be, a third-party service that specializes in providing (e.g., offering, renting, selling) IaaS. An entity might also opt to deploy a private cloud, becoming its own provider of infrastructure services.

In some examples, IaaS deployment is the process of putting a new application, or a new version of an application, onto a prepared application server or the like. It may also include the process of preparing the server (e.g., installing libraries, daemons, etc.). This is often managed by the cloud provider, below the hypervisor layer (e.g., the servers, storage, network hardware, and virtualization). Thus, the customer may be responsible for handling (OS), middleware, and/or application deployment (e.g., on self-service virtual machines (e.g., that can be spun up on demand) or the like.

In some examples, IaaS provisioning may refer to acquiring computers or virtual hosts for use, and even installing needed libraries or services on them. In most cases, deployment does not include provisioning, and the provisioning may need to be performed first.

In some cases, there are two different challenges for IaaS provisioning. First, there is the initial challenge of provisioning the initial set of infrastructure before anything is running. Second, there is the challenge of evolving the existing infrastructure (e.g., adding new services, changing services, removing services, etc.) once everything has been provisioned. In some cases, these two challenges may be addressed by enabling the configuration of the infrastructure to be defined declaratively. In other words, the infrastructure (e.g., what components are needed and how they interact) can be defined by one or more configuration files. Thus, the overall topology of the infrastructure (e.g., what resources depend on which, and how they each work together) can be described declaratively. In some instances, once the topology is defined, a workflow can be generated that creates and/or manages the different components described in the configuration files.

In some examples, an infrastructure may have many interconnected elements. For example, there may be one or more virtual private clouds (VPCs) (e.g., a potentially on-demand pool of configurable and/or shared computing resources), also known as a core network. In some examples, there may also be one or more security group rules provisioned to define how the security of the network will be set up and one or more virtual machines (VMs). Other infrastructure elements may also be provisioned, such as a load balancer, a database, or the like. As more and more infrastructure elements are desired and/or added, the infrastructure may incrementally evolve.

In some instances, continuous deployment techniques may be employed to enable deployment of infrastructure code across various virtual computing environments. Additionally, the described techniques can enable infrastructure management within these environments. In some examples, service teams can write code that is desired to be deployed to one or more, but often many, different production environments (e.g., across various different geographic locations, sometimes spanning the entire world). However, in some examples, the infrastructure on which the code will be deployed must first be set up. In some instances, the provisioning can be done manually, a provisioning tool may be utilized to provision the resources, and/or deployment tools may be utilized to deploy the code once the infrastructure is provisioned.

16 FIG. 1600 1602 1604 1606 1608 1602 8 1606 is a block diagramillustrating an example pattern of an IaaS architecture, according to at least one embodiment. Service operatorscan be communicatively coupled to a secure host tenancythat can include a virtual cloud network (VCN)and a secure host subnet. In some examples, the service operatorsmay be using one or more client computing devices, which may be portable handheld devices (e.g., an iPhone®, cellular telephone, an iPad®, computing tablet, a personal digital assistant (PDA)) or wearable devices (e.g., a Google Glass® head mounted display), running software such as Microsoft Windows Mobile®, and/or a variety of mobile operating systems such as iOS, Windows Phone, Android, BlackBerry, Palm OS, and the like, and being Internet, e-mail, short message service (SMS), Blackberry®, or other communication protocol enabled. Alternatively, the client computing devices can be general purpose personal computers including, by way of example, personal computers and/or laptop computers running various versions of Microsoft Windows®, Apple Macintosh®, and/or Linux operating systems. The client computing devices can be workstation computers running any of a variety of commercially-available UNIX® or UNIX-like operating systems, including without limitation the variety of GNU/Linux operating systems, such as for example, Google Chrome OS. Alternatively, or in addition, client computing devices may be any other electronic device, such as a thin-client computer, an Internet-enabled gaming system (e.g., a Microsoft Xbox gaming console with or without a Kinect® gesture input device), and/or a personal messaging device, capable of communicating over a network that can access the VCNand/or the Internet.

1606 1610 1612 1610 1612 1612 1614 1612 1616 1610 1616 1612 1618 1610 1616 1618 1619 The VCNcan include a local peering gateway (LPG)that can be communicatively coupled to a secure shell (SSH) VCNvia an LPGcontained in the SSH VCN. The SSH VCNcan include an SSH subnet, and the SSH VCNcan be communicatively coupled to a control plane VCNvia the LPGcontained in the control plane VCN. Also, the SSH VCNcan be communicatively coupled to a data plane VCNvia an LPG. The control plane VCNand the data plane VCNcan be contained in a service tenancythat can be owned and/or operated by the IaaS provider.

1616 1620 1620 1622 1624 1626 1628 1630 1622 1620 1626 1624 1634 1616 1626 1630 1628 1636 1638 1616 1636 1638 The control plane VCNcan include a control plane demilitarized zone (DMZ) tierthat acts as a perimeter network (e.g., portions of a corporate network between the corporate intranet and external networks). The DMZ-based servers may have restricted responsibilities and help keep security breaches contained. Additionally, the DMZ tiercan include one or more load balancer (LB) subnet(s), a control plane app tierthat can include app subnet(s), a control plane data tierthat can include database (DB) subnet(s)(e.g., frontend DB subnet(s) and/or backend DB subnet(s)). The LB subnet(s)contained in the control plane DMZ tiercan be communicatively coupled to the app subnet(s)contained in the control plane app tierand an Internet gatewaythat can be contained in the control plane VCN, and the app subnet(s)can be communicatively coupled to the DB subnet(s)contained in the control plane data tierand a service gatewayand a network address translation (NAT) gateway. The control plane VCNcan include the service gatewayand the NAT gateway.

1616 1640 1626 1626 1640 1642 1644 1644 1626 1640 1626 1646 The control plane VCNcan include a data plane mirror app tierthat can include app subnet(s). The app subnet(s)contained in the data plane mirror app tiercan include a virtual network interface controller (VNIC)that can execute a compute instance. The compute instancecan communicatively couple the app subnet(s)of the data plane mirror app tierto app subnet(s)that can be contained in a data plane app tier.

1618 1646 1648 1650 1648 1622 1626 1646 1634 1618 1626 1636 1618 1638 1618 1650 1630 1626 1646 The data plane VCNcan include the data plane app tier, a data plane DMZ tier, and a data plane data tier. The data plane DMZ tiercan include LB subnet(s)that can be communicatively coupled to the app subnet(s)of the data plane app tierand the Internet gatewayof the data plane VCN. The app subnet(s)can be communicatively coupled to the service gatewayof the data plane VCNand the NAT gatewayof the data plane VCN. The data plane data tiercan also include the DB subnet(s)that can be communicatively coupled to the app subnet(s)of the data plane app tier.

1634 1616 1618 1652 1654 1654 1638 1616 1618 1636 1616 1618 1656 The Internet gatewayof the control plane VCNand of the data plane VCNcan be communicatively coupled to a metadata management servicethat can be communicatively coupled to public Internet. Public Internetcan be communicatively coupled to the NAT gatewayof the control plane VCNand of the data plane VCN. The service gatewayof the control plane VCNand of the data plane VCNcan be communicatively couple to cloud services.

1636 1616 1618 1656 1654 1656 1636 1636 1656 1656 1636 1656 1636 In some examples, the service gatewayof the control plane VCNor of the data plane VCNcan make application programming interface (API) calls to cloud serviceswithout going through public Internet. The API calls to cloud servicesfrom the service gatewaycan be one-way: the service gatewaycan make API calls to cloud services, and cloud servicescan send requested data to the service gateway. But, cloud servicesmay not initiate API calls to the service gateway.

1604 1619 1608 1614 1610 1608 1614 1608 1619 In some examples, the secure host tenancycan be directly connected to the service tenancy, which may be otherwise isolated. The secure host subnetcan communicate with the SSH subnetthrough an LPGthat may enable two-way communication over an otherwise isolated system. Connecting the secure host subnetto the SSH subnetmay give the secure host subnetaccess to other entities within the service tenancy.

1616 1619 1616 1618 1616 1618 1640 1616 1646 1618 1642 1640 1646 The control plane VCNmay allow users of the service tenancyto set up or otherwise provision desired resources. Desired resources provisioned in the control plane VCNmay be deployed or otherwise used in the data plane VCN. In some examples, the control plane VCNcan be isolated from the data plane VCN, and the data plane mirror app tierof the control plane VCNcan communicate with the data plane app tierof the data plane VCNvia VNICsthat can be contained in the data plane mirror app tierand the data plane app tier.

1654 1652 1652 1616 1634 1622 1620 1622 1622 1626 1624 1654 1654 1638 1654 1630 In some examples, users of the system, or customers, can make requests, for example create, read, update, or delete (CRUD) operations, through public Internetthat can communicate the requests to the metadata management service. The metadata management servicecan communicate the request to the control plane VCNthrough the Internet gateway. The request can be received by the LB subnet(s)contained in the control plane DMZ tier. The LB subnet(s)may determine that the request is valid, and in response to this determination, the LB subnet(s)can transmit the request to app subnet(s)contained in the control plane app tier. If the request is validated and requires a call to public Internet, the call to public Internetmay be transmitted to the NAT gatewaythat can make the call to public Internet. Memory that may be desired to be stored by the request can be stored in the DB subnet(s).

1640 1616 1618 1618 1642 1616 1618 In some examples, the data plane mirror app tiercan facilitate direct communication between the control plane VCNand the data plane VCN. For example, changes, updates, or other suitable modifications to configuration may be desired to be applied to the resources contained in the data plane VCN. Via a VNIC, the control plane VCNcan directly communicate with, and can thereby execute the changes, updates, or other suitable modifications to configuration to, resources contained in the data plane VCN.

1616 1618 1619 1616 1618 1616 1618 1619 1654 In some embodiments, the control plane VCNand the data plane VCNcan be contained in the service tenancy. In this case, the user, or the customer, of the system may not own or operate either the control plane VCNor the data plane VCN. Instead, the IaaS provider may own or operate the control plane VCNand the data plane VCN, both of which may be contained in the service tenancy. This embodiment can enable isolation of networks that may prevent users or customers from interacting with other users', or other customers', resources. Also, this embodiment may allow users or customers of the system to store databases privately without needing to rely on public Internet, which may not have a desired level of security, for storage.

1622 1616 1636 1616 1618 1654 1619 1654 In other embodiments, the LB subnet(s)contained in the control plane VCNcan be configured to receive a signal from the service gateway. In this embodiment, the control plane VCNand the data plane VCNmay be configured to be called by a customer of the IaaS provider without calling public Internet. Customers of the IaaS provider may desire this embodiment since database(s) that the customers use may be controlled by the IaaS provider and may be stored on the service tenancy, which may be isolated from public Internet.

17 FIG. 16 FIG. 16 FIG. 16 FIG. 16 FIG. 16 FIG. 16 FIG. 16 FIG. 16 FIG. 16 FIG. 16 FIG. 1700 1702 1602 1704 1604 1706 1606 1708 1608 1706 1710 1610 1712 1612 1710 1712 1712 1714 1614 1712 1716 1616 1710 1716 1716 1719 1619 1718 1618 1721 is a block diagramillustrating another example pattern of an IaaS architecture, according to at least one embodiment. Service operators(e.g., service operatorsof) can be communicatively coupled to a secure host tenancy(e.g., the secure host tenancyof) that can include a virtual cloud network (VCN)(e.g., the VCNof) and a secure host subnet(e.g., the secure host subnetof). The VCNcan include a local peering gateway (LPG)(e.g., the LPGof) that can be communicatively coupled to a secure shell (SSH) VCN(e.g., the SSH VCNof) via an LPGcontained in the SSH VCN. The SSH VCNcan include an SSH subnet(e.g., the SSH subnetof), and the SSH VCNcan be communicatively coupled to a control plane VCN(e.g., the control plane VCNof) via an LPGcontained in the control plane VCN. The control plane VCNcan be contained in a service tenancy(e.g., the service tenancyof), and the data plane VCN(e.g., the data plane VCNof) can be contained in a customer tenancythat may be owned or operated by users, or customers, of the system.

1716 1720 1620 1722 1622 1724 1624 1726 1626 1728 1628 1730 1630 1722 1720 1726 1724 1734 1634 1716 1726 1730 1728 1736 1738 1638 1716 1736 1738 16 FIG. 16 FIG. 16 FIG. 16 FIG. 16 FIG. 16 FIG. 16 FIG. 16 FIG. 16 FIG. The control plane VCNcan include a control plane DMZ tier(e.g. the control plane DMZ tierof) that can include LB subnet(s)(e.g. LB subnet(s)of), a control plane app tier(e.g. the control plane app tierof) that can include app subnet(s)(e.g. app subnet(s)of), a control plane data tier(e.g. the control plane data tierof) that can include database (DB) subnet(s)(e.g. similar to DB subnet(s)of). The LB subnet(s)contained in the control plane DMZ tiercan be communicatively coupled to the app subnet(s)contained in the control plane app tierand an Internet gateway(e.g. the Internet gatewayof) that can be contained in the control plane VCN, and the app subnet(s)can be communicatively coupled to the DB subnet(s)contained in the control plane data tierand a service gateway(e.g. the service gateway of) and a network address translation (NAT) gateway(e.g. the NAT gatewayof). The control plane VCNcan include the service gatewayand the NAT gateway.

1716 1740 1640 1726 1726 1740 1742 1642 1744 1644 1744 1726 1740 1726 1746 1646 1742 1740 1742 1746 16 FIG. 16 FIG. 16 FIG. The control plane VCNcan include a data plane mirror app tier(e.g., the data plane mirror app tierof) that can include app subnet(s). The app subnet(s)contained in the data plane mirror app tiercan include a virtual network interface controller (VNIC)(e.g., the VNIC of) that can execute a compute instance(e.g., similar to the compute instanceof). The compute instancecan facilitate communication between the app subnet(s)of the data plane mirror app tierand the app subnet(s)that can be contained in a data plane app tier(e.g., the data plane app tierof) via the VNICcontained in the data plane mirror app tierand the VNICcontained in the data plane app tier.

1734 1716 1752 1652 1754 1654 1754 1738 1716 1736 1716 1756 1656 16 FIG. 16 FIG. 16 FIG. The Internet gatewaycontained in the control plane VCNcan be communicatively coupled to a metadata management service(e.g., the metadata management serviceof) that can be communicatively coupled to public Internet(e.g., public Internetof). Public Internetcan be communicatively coupled to the NAT gatewaycontained in the control plane VCN. The service gatewaycontained in the control plane VCNcan be communicatively couple to cloud services(e.g., cloud servicesof).

1718 1721 1716 1744 1719 1744 1716 1719 1718 1721 1744 1716 1719 1718 1721 In some examples, the data plane VCNcan be contained in the customer tenancy. In this case, the IaaS provider may provide the control plane VCNfor each customer, and the IaaS provider may, for each customer, set up a unique compute instancethat is contained in the service tenancy. Each compute instancemay allow communication between the control plane VCN, contained in the service tenancy, and the data plane VCNthat is contained in the customer tenancy. The compute instancemay allow resources that are provisioned in the control plane VCNthat is contained in the service tenancy, to be deployed or otherwise used in the data plane VCNthat is contained in the customer tenancy.

1721 1716 1740 1726 1740 1718 1740 1718 1740 1721 1740 1718 1740 1718 1716 1718 1716 1740 In other examples, the customer of the IaaS provider may have databases that live in the customer tenancy. In this example, the control plane VCNcan include the data plane mirror app tierthat can include app subnet(s). The data plane mirror app tiercan reside in the data plane VCN, but the data plane mirror app tiermay not live in the data plane VCN. That is, the data plane mirror app tiermay have access to the customer tenancy, but the data plane mirror app tiermay not exist in the data plane VCNor be owned or operated by the customer of the IaaS provider. The data plane mirror app tiermay be configured to make calls to the data plane VCNbut may not be configured to make calls to any entity contained in the control plane VCN. The customer may desire to deploy or otherwise use resources in the data plane VCNthat are provisioned in the control plane VCN, and the data plane mirror app tiercan facilitate the desired deployment, or other usage of resources, of the customer.

1718 1718 1754 1718 1718 1718 1721 1718 1754 In some embodiments, the customer of the IaaS provider can apply filters to the data plane VCN. In this embodiment, the customer can determine what the data plane VCNcan access, and the customer may restrict access to public Internetfrom the data plane VCN. The IaaS provider may not be able to apply filters or otherwise control access of the data plane VCNto any outside networks or databases. Applying filters and controls by the customer onto the data plane VCN, contained in the customer tenancy, can help isolate the data plane VCNfrom other customers and from public Internet.

1756 1736 1754 1716 1718 1756 1716 1718 1756 1756 1736 1754 1756 1756 1716 1756 1716 1716 1 16 1 2 16 1736 1716 1 16 1 1716 16 1 16 2 In some embodiments, cloud servicescan be called by the service gatewayto access services that may not exist on public Internet, on the control plane VCN, or on the data plane VCN. The connection between cloud servicesand the control plane VCNor the data plane VCNmay not be live or continuous. Cloud servicesmay exist on a different network owned or operated by the IaaS provider. Cloud servicesmay be configured to receive calls from the service gatewayand may be configured to not receive calls from public Internet. Some cloud servicesmay be isolated from other cloud services, and the control plane VCNmay be isolated from cloud servicesthat may not be in the same region as the control plane VCN. For example, the control plane VCNmay be located in “Region,” and cloud service “Deployment,” may be located in Regionand in “Region.” If a call to Deploymentis made by the service gatewaycontained in the control plane VCNlocated in Region, the call may be transmitted to Deploymentin Region. In this example, the control plane VCN, or Deploymentin Region, may not be communicatively coupled to, or otherwise in communication with, Deploymentin Region.

18 FIG. 16 FIG. 16 FIG. 16 FIG. 16 FIG. 16 FIG. 16 FIG. 16 FIG. 16 FIG. 16 FIG. 16 FIG. 1800 1802 1602 1804 1604 1806 1606 1808 1608 1806 1810 1610 1812 1612 1810 1812 1812 1814 1614 1812 1816 1616 1810 1816 1818 1618 1810 1818 1816 1818 1819 1619 is a block diagramillustrating another example pattern of an IaaS architecture, according to at least one embodiment. Service operators(e.g., service operatorsof) can be communicatively coupled to a secure host tenancy(e.g., the secure host tenancyof) that can include a virtual cloud network (VCN)(e.g., the VCNof) and a secure host subnet(e.g., the secure host subnetof). The VCNcan include an LPG(e.g., the LPGof) that can be communicatively coupled to an SSH VCN(e.g., the SSH VCNof) via an LPGcontained in the SSH VCN. The SSH VCNcan include an SSH subnet(e.g., the SSH subnetof), and the SSH VCNcan be communicatively coupled to a control plane VCN(e.g., the control plane VCNof) via an LPGcontained in the control plane VCNand to a data plane VCN(e.g., the data planeof) via an LPGcontained in the data plane VCN. The control plane VCNand the data plane VCNcan be contained in a service tenancy(e.g., the service tenancyof).

1816 1820 1620 1822 1622 1824 1624 1826 1626 1828 1628 1830 1822 1820 1826 1824 1834 1634 1816 1826 1830 1828 1836 1838 1638 1816 1836 1838 16 FIG. 16 FIG. 16 FIG. 16 FIG. 16 FIG. 16 FIG. 16 FIG. 16 FIG. The control plane VCNcan include a control plane DMZ tier(e.g. the control plane DMZ tierof) that can include load balancer (LB) subnet(s)(e.g. LB subnet(s)of), a control plane app tier(e.g. the control plane app tierof) that can include app subnet(s)(e.g. similar to app subnet(s)of), a control plane data tier(e.g. the control plane data tierof) that can include DB subnet(s). The LB subnet(s)contained in the control plane DMZ tiercan be communicatively coupled to the app subnet(s)contained in the control plane app tierand to an Internet gateway(e.g. the Internet gatewayof) that can be contained in the control plane VCN, and the app subnet(s)can be communicatively coupled to the DB subnet(s)contained in the control plane data tierand to a service gateway(e.g. the service gateway of) and a network address translation (NAT) gateway(e.g. the NAT gatewayof). The control plane VCNcan include the service gatewayand the NAT gateway.

1818 1846 1646 1848 1648 1850 1650 1848 1822 1860 1862 1846 1834 1818 1860 1836 1818 1838 1818 1830 1850 1862 1836 1818 1830 1850 1850 1830 1836 1818 16 FIG. 16 FIG. 16 FIG. The data plane VCNcan include a data plane app tier(e.g., the data plane app tierof), a data plane DMZ tier(e.g., the data plane DMZ tierof), and a data plane data tier(e.g., the data plane data tierof). The data plane DMZ tiercan include LB subnet(s)that can be communicatively coupled to trusted app subnet(s)and untrusted app subnet(s)of the data plane app tierand the Internet gatewaycontained in the data plane VCN. The trusted app subnet(s)can be communicatively coupled to the service gatewaycontained in the data plane VCN, the NAT gatewaycontained in the data plane VCN, and DB subnet(s)contained in the data plane data tier. The untrusted app subnet(s)can be communicatively coupled to the service gatewaycontained in the data plane VCNand DB subnet(s)contained in the data plane data tier. The data plane data tiercan include DB subnet(s)that can be communicatively coupled to the service gatewaycontained in the data plane VCN.

1862 1864 1 1866 1 1866 1 1867 1 1868 1 1870 1 1872 1 1862 1818 1868 1 1868 1 1838 1854 1654 16 FIG. The untrusted app subnet(s)can include one or more primary VNICs()-(N) that can be communicatively coupled to tenant virtual machines (VMs)()-(N). Each tenant VM()-(N) can be communicatively coupled to a respective app subnet()-(N) that can be contained in respective container egress VCNs()-(N) that can be contained in respective customer tenancies()-(N). Respective secondary VNICs()-(N) can facilitate communication between the untrusted app subnet(s)contained in the data plane VCNand the app subnet contained in the container egress VCNs()-(N). Each container egress VCNs()-(N) can include a NAT gatewaythat can be communicatively coupled to public Internet(e.g., public Internetof).

1834 1816 1818 1852 1652 1854 1854 1838 1816 1818 1836 1816 1818 1856 16 FIG. The Internet gatewaycontained in the control plane VCNand contained in the data plane VCNcan be communicatively coupled to a metadata management service(e.g., the metadata management systemof) that can be communicatively coupled to public Internet. Public Internetcan be communicatively coupled to the NAT gatewaycontained in the control plane VCNand contained in the data plane VCN. The service gatewaycontained in the control plane VCNand contained in the data plane VCNcan be communicatively couple to cloud services.

1818 1870 In some embodiments, the data plane VCNcan be integrated with customer tenancies. This integration can be useful or desirable for customers of the IaaS provider in some cases such as a case that may desire support when executing code. The customer may provide code to run that may be destructive, may communicate with other customer resources, or may otherwise cause undesirable effects. In response to this, the IaaS provider may determine whether to run code given to the IaaS provider by the customer.

1846 1866 1 1818 1866 1 1870 1871 1 1866 1 1871 1 1871 1 1866 1 1862 1871 1 1870 1870 1871 1 1818 1871 1 In some examples, the customer of the IaaS provider may grant temporary network access to the IaaS provider and request a function to be attached to the data plane tier app. Code to run the function may be executed in the VMs()-(N), and the code may not be configured to run anywhere else on the data plane VCN. Each VM()-(N) may be connected to one customer tenancy. Respective containers()-(N) contained in the VMs()-(N) may be configured to run the code. In this case, there can be a dual isolation (e.g., the containers()-(N) running code, where the containers()-(N) may be contained in at least the VM()-(N) that are contained in the untrusted app subnet(s)), which may help prevent incorrect or otherwise undesirable code from damaging the network of the IaaS provider or from damaging a network of a different customer. The containers()-(N) may be communicatively coupled to the customer tenancyand may be configured to transmit or receive data from the customer tenancy. The containers()-(N) may not be configured to transmit or receive data from any other entity in the data plane VCN. Upon completion of running the code, the IaaS provider may kill or otherwise dispose of the containers()-(N).

1860 1860 1830 1830 1862 1830 1830 1871 1 1866 1 1830 In some embodiments, the trusted app subnet(s)may run code that may be owned or operated by the IaaS provider. In this embodiment, the trusted app subnet(s)may be communicatively coupled to the DB subnet(s)and be configured to execute CRUD operations in the DB subnet(s). The untrusted app subnet(s)may be communicatively coupled to the DB subnet(s), but in this embodiment, the untrusted app subnet(s) may be configured to execute read operations in the DB subnet(s). The containers()-(N) that can be contained in the VM()-(N) of each customer and that may run code from the customer may not be communicatively coupled with the DB subnet(s).

1816 1818 1816 1818 1810 1816 1818 1816 1818 1856 1836 1856 1816 1818 In other embodiments, the control plane VCNand the data plane VCNmay not be directly communicatively coupled. In this embodiment, there may be no direct communication between the control plane VCNand the data plane VCN. However, communication can occur indirectly through at least one method. An LPGmay be established by the IaaS provider that can facilitate communication between the control plane VCNand the data plane VCN. In another example, the control plane VCNor the data plane VCNcan make a call to cloud servicesvia the service gateway. For example, a call to cloud servicesfrom the control plane VCNcan include a request for a service that can communicate with the data plane VCN.

19 FIG. 16 FIG. 16 FIG. 16 FIG. 16 FIG. 16 FIG. 16 FIG. 16 FIG. 16 FIG. 16 FIG. 16 FIG. 1900 1902 1602 1904 1604 1906 1606 1908 1608 1906 1910 1610 1912 1612 1910 1912 1912 1914 1614 1912 1916 1616 1910 1916 1918 1618 1910 1918 1916 1918 1919 1619 is a block diagramillustrating another example pattern of an IaaS architecture, according to at least one embodiment. Service operators(e.g., service operatorsof) can be communicatively coupled to a secure host tenancy(e.g., the secure host tenancyof) that can include a virtual cloud network (VCN)(e.g., the VCNof) and a secure host subnet(e.g., the secure host subnetof). The VCNcan include an LPG(e.g., the LPGof) that can be communicatively coupled to an SSH VCN(e.g., the SSH VCNof) via an LPGcontained in the SSH VCN. The SSH VCNcan include an SSH subnet(e.g., the SSH subnetof), and the SSH VCNcan be communicatively coupled to a control plane VCN(e.g., the control plane VCNof) via an LPGcontained in the control plane VCNand to a data plane VCN(e.g., the data planeof) via an LPGcontained in the data plane VCN. The control plane VCNand the data plane VCNcan be contained in a service tenancy(e.g., the service tenancyof).

1916 1920 1620 1922 1622 1924 1624 1926 1626 1928 1628 1930 1830 1922 1920 1926 1924 1934 1634 1916 1926 1930 1928 1936 1938 1638 1916 1936 1938 16 FIG. 16 FIG. 16 FIG. 16 FIG. 16 FIG. 18 FIG. 16 FIG. 16 FIG. 16 FIG. The control plane VCNcan include a control plane DMZ tier(e.g. the control plane DMZ tierof) that can include LB subnet(s)(e.g. LB subnet(s)of), a control plane app tier(e.g. the control plane app tierof) that can include app subnet(s)(e.g. app subnet(s)of), a control plane data tier(e.g. the control plane data tierof) that can include DB subnet(s)(e.g. DB subnet(s)of). The LB subnet(s)contained in the control plane DMZ tiercan be communicatively coupled to the app subnet(s)contained in the control plane app tierand to an Internet gateway(e.g. the Internet gatewayof) that can be contained in the control plane VCN, and the app subnet(s)can be communicatively coupled to the DB subnet(s)contained in the control plane data tierand to a service gateway(e.g. the service gateway of) and a network address translation (NAT) gateway(e.g. the NAT gatewayof). The control plane VCNcan include the service gatewayand the NAT gateway.

1918 1946 1646 1948 1648 1950 1650 1948 1922 1960 1860 1962 1862 1946 1934 1918 1960 1936 1918 1938 1918 1930 1950 1962 1936 1918 1930 1950 1950 1930 1936 1918 16 FIG. 16 FIG. 16 FIG. 18 FIG. 18 FIG. The data plane VCNcan include a data plane app tier(e.g., the data plane app tierof), a data plane DMZ tier(e.g., the data plane DMZ tierof), and a data plane data tier(e.g., the data plane data tierof). The data plane DMZ tiercan include LB subnet(s)that can be communicatively coupled to trusted app subnet(s)(e.g., trusted app subnet(s)of) and untrusted app subnet(s)(e.g., untrusted app subnet(s)of) of the data plane app tierand the Internet gatewaycontained in the data plane VCN. The trusted app subnet(s)can be communicatively coupled to the service gatewaycontained in the data plane VCN, the NAT gatewaycontained in the data plane VCN, and DB subnet(s)contained in the data plane data tier. The untrusted app subnet(s)can be communicatively coupled to the service gatewaycontained in the data plane VCNand DB subnet(s)contained in the data plane data tier. The data plane data tiercan include DB subnet(s)that can be communicatively coupled to the service gatewaycontained in the data plane VCN.

1962 1964 1 1966 1 1962 1966 1 1967 1 1926 1946 1968 1972 1 1962 1918 1968 1938 1954 1654 16 FIG. The untrusted app subnet(s)can include primary VNICs()-(N) that can be communicatively coupled to tenant virtual machines (VMs)()-(N) residing within the untrusted app subnet(s). Each tenant VM()-(N) can run code in a respective container()-(N) and be communicatively coupled to an app subnetthat can be contained in a data plane app tierthat can be contained in a container egress VCN. Respective secondary VNICs()-(N) can facilitate communication between the untrusted app subnet(s)contained in the data plane VCNand the app subnet contained in the container egress VCN. The container egress VCN can include a NAT gatewaythat can be communicatively coupled to public Internet(e.g., public Internetof).

1934 1916 1918 1952 1652 1954 1954 1938 1916 1918 1936 1916 1918 1956 16 FIG. The Internet gatewaycontained in the control plane VCNand contained in the data plane VCNcan be communicatively coupled to a metadata management service(e.g., the metadata management systemof) that can be communicatively coupled to public Internet. Public Internetcan be communicatively coupled to the NAT gatewaycontained in the control plane VCNand contained in the data plane VCN. The service gatewaycontained in the control plane VCNand contained in the data plane VCNcan be communicatively couple to cloud services.

1900 1800 1967 1 1966 1 1967 1 1972 1 1926 1946 1968 1972 1 1938 1954 1967 1 1916 1918 1967 1 19 FIG. 18 FIG. In some examples, the pattern illustrated by the architecture of block diagramofmay be considered an exception to the pattern illustrated by the architecture of block diagramofand may be desirable for a customer of the IaaS provider if the IaaS provider cannot directly communicate with the customer (e.g., a disconnected region). The respective containers()-(N) that are contained in the VMs()-(N) for each customer can be accessed in real-time by the customer. The containers()-(N) may be configured to make calls to respective secondary VNICs()-(N) contained in app subnet(s)of the data plane app tierthat can be contained in the container egress VCN. The secondary VNICs()-(N) can transmit the calls to the NAT gatewaythat may transmit the calls to public Internet. In this example, the containers()-(N) that can be accessed in real-time by the customer can be isolated from the control plane VCNand can be isolated from other entities contained in the data plane VCN. The containers()-(N) may also be isolated from resources from other customers.

1967 1 1956 1967 1 1956 1967 1 1972 1 1954 1954 1922 1916 1934 1926 1956 1936 In other examples, the customer can use the containers()-(N) to call cloud services. In this example, the customer may run code in the containers()-(N) that requests a service from cloud services. The containers()-(N) can transmit this request to the secondary VNICs()-(N) that can transmit the request to the NAT gateway that can transmit the request to public Internet. Public Internetcan transmit the request to LB subnet(s)contained in the control plane VCNvia the Internet gateway. In response to determining the request is valid, the LB subnet(s) can transmit the request to app subnet(s)that can transmit the request to cloud servicesvia the service gateway.

1600 1700 1800 1900 It should be appreciated that IaaS architectures,,,depicted in the figures may have other components than those depicted. Further, the embodiments shown in the figures are only some examples of a cloud infrastructure system that may incorporate an embodiment of the disclosure. In some other embodiments, the IaaS systems may have more or fewer components than shown in the figures, may combine two or more components, or may have a different configuration or arrangement of components.

In certain embodiments, the IaaS systems described herein may include a suite of applications, middleware, and database service offerings that are delivered to a customer in a self-service, subscription-based, elastically scalable, reliable, highly available, and secure manner. An example of such an IaaS system is the Oracle Cloud Infrastructure (OCI) provided by the present assignee.

20 FIG. 2000 2000 2000 2004 2002 2006 2008 2018 2024 2018 2022 2010 illustrates an example computer system, in which various embodiments may be implemented. The systemmay be used to implement any of the computer systems described above. As shown in the figure, computer systemincludes a processing unitthat communicates with a number of peripheral subsystems via a bus subsystem. These peripheral subsystems may include a processing acceleration unit, and I/O subsystem, a storage subsystemand a communications subsystem. Storage subsystemincludes tangible computer-readable storage mediaand a system memory.

2002 2000 2002 2002 Bus subsystemprovides a mechanism for letting the various components and subsystems of computer systemcommunicate with each other as intended. Although bus subsystemis shown schematically as a single bus, alternative embodiments of the bus subsystem may utilize multiple buses. Bus subsystemmay be any of several types of bus structures including a memory bus or memory controller, a peripheral bus, and a local bus using any of a variety of bus architectures. For example, such architectures may include an Industry Standard Architecture (ISA) bus, Micro Channel Architecture (MCA) bus, Enhanced ISA (EISA) bus, Video Electronics Standards Association (VESA) local bus, and Peripheral Component Interconnect (PCI) bus, which can be implemented as a Mezzanine bus manufactured to the IEEE P1386.1 standard.

2004 2000 2004 2004 2032 2034 2004 Processing unit, which can be implemented as one or more integrated circuits (e.g., a conventional microprocessor or microcontroller), controls the operation of computer system. One or more processors may be included in processing unit. These processors may include single core or multicore processors. In certain embodiments, processing unitmay be implemented as one or more independent processing unitsand/orwith single or multicore processors included in each processing unit. In other embodiments, processing unitmay also be implemented as a quad-core processing unit formed by integrating two dual-core processors into a single chip.

2004 2004 2018 2004 2000 2006 In various embodiments, processing unitcan execute a variety of programs in response to program code and can maintain multiple concurrently executing programs or processes. At any given time, some or all of the program code to be executed can be resident in processor(s)and/or in storage subsystem. Through suitable programming, processor(s)can provide various functionalities described above. Computer systemmay additionally include a processing acceleration unit, which can include a digital signal processor (DSP), a special-purpose processor, and/or the like.

2008 I/O subsystemmay include user interface input devices and user interface output devices. User interface input devices may include a keyboard, pointing devices such as a mouse or trackball, a touchpad or touch screen incorporated into a display, a scroll wheel, a click wheel, a dial, a button, a switch, a keypad, audio input devices with voice command recognition systems, microphones, and other types of input devices. User interface input devices may include, for example, motion sensing and/or gesture recognition devices such as the Microsoft Kinect® motion sensor that enables users to control and interact with an input device, such as the Microsoft Xbox® 360 game controller, through a natural user interface using gestures and spoken commands. User interface input devices may also include eye gesture recognition devices such as the Google Glass® blink detector that detects eye activity (e.g., ‘blinking’ while taking pictures and/or making a menu selection) from users and transforms the eye gestures as input into an input device (e.g., Google Glass®). Additionally, user interface input devices may include voice recognition sensing devices that enable users to interact with voice recognition systems (e.g., Siri® navigator), through voice commands.

User interface input devices may also include, without limitation, three dimensional (3D) mice, joysticks or pointing sticks, gamepads and graphic tablets, and audio/visual devices such as speakers, digital cameras, digital camcorders, portable media players, webcams, image scanners, fingerprint scanners, barcode reader 3D scanners, 3D printers, laser rangefinders, and eye gaze tracking devices. Additionally, user interface input devices may include, for example, medical imaging input devices such as computed tomography, magnetic resonance imaging, position emission tomography, medical ultrasonography devices. User interface input devices may also include, for example, audio input devices such as MIDI keyboards, digital musical instruments and the like.

2000 User interface output devices may include a display subsystem, indicator lights, or non-visual displays such as audio output devices, etc. The display subsystem may be a cathode ray tube (CRT), a flat-panel device, such as that using a liquid crystal display (LCD) or plasma display, a projection device, a touch screen, and the like. In general, use of the term “output device” is intended to include all possible types of devices and mechanisms for outputting information from computer systemto a user or other computer. For example, user interface output devices may include, without limitation, a variety of display devices that visually convey text, graphics and audio/video information such as monitors, printers, speakers, headphones, automotive navigation systems, plotters, voice output devices, and modems.

2000 2018 2010 2010 2004 Computer systemmay comprise a storage subsystemthat comprises software elements, shown as being currently located within a system memory. System memorymay store program instructions that are loadable and executable on processing unit, as well as data generated during the execution of these programs.

2000 2010 2004 2010 2000 2010 2012 2014 2016 2016 Depending on the configuration and type of computer system, system memorymay be volatile (such as random access memory (RAM)) and/or non-volatile (such as read-only memory (ROM), flash memory, etc.) The RAM typically contains data and/or program modules that are immediately accessible to and/or presently being operated and executed by processing unit. In some implementations, system memorymay include multiple different types of memory, such as static random access memory (SRAM) or dynamic random access memory (DRAM). In some implementations, a basic input/output system (BIOS), containing the basic routines that help to transfer information between elements within computer system, such as during start-up, may typically be stored in the ROM. By way of example, and not limitation, system memoryalso illustrates application programs, which may include client applications, Web browsers, mid-tier applications, relational database management systems (RDBMS), etc., program data, and an operating system. By way of example, operating systemmay include various versions of Microsoft Windows®, Apple Macintosh®, and/or Linux operating systems, a variety of commercially-available UNIX® or UNIX-like operating systems (including without limitation the variety of GNU/Linux operating systems, the Google Chrome® OS, and the like) and/or mobile operating systems such as iOS, Windows® Phone, Android® OS, BlackBerry® 20 OS, and Palm® OS operating systems.

2018 2018 2004 2018 Storage subsystemmay also provide a tangible computer-readable storage medium for storing the basic programming and data constructs that provide the functionality of some embodiments. Software (programs, code modules, instructions) that when executed by a processor provide the functionality described above may be stored in storage subsystem. These software modules or instructions may be executed by processing unit. Storage subsystemmay also provide a repository for storing data used in accordance with the present disclosure.

2000 2020 2022 2010 2022 Storage subsystemmay also include a computer-readable storage media readerthat can further be connected to computer-readable storage media. Together and optionally, in combination with system memory, computer-readable storage mediamay comprehensively represent remote, local, fixed, and/or removable storage devices plus storage media for temporarily and/or more permanently containing, storing, transmitting, and retrieving computer-readable information.

2022 2000 Computer-readable storage mediacontaining code, or portions of code, can also include any appropriate media known or used in the art, including storage media and communication media, such as but not limited to, volatile and non-volatile, removable and non-removable media implemented in any method or technology for storage and/or transmission of information. This can include tangible computer-readable storage media such as RAM, ROM, electronically erasable programmable ROM (EEPROM), flash memory or other memory technology, CD-ROM, digital versatile disk (DVD), or other optical storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices, or other tangible computer readable media. This can also include nontangible computer-readable media, such as data signals, data transmissions, or any other medium which can be used to transmit the desired information, and which can be accessed by computing system.

2022 2022 2022 2000 By way of example, computer-readable storage mediamay include a hard disk drive that reads from or writes to non-removable, nonvolatile magnetic media, a magnetic disk drive that reads from or writes to a removable, nonvolatile magnetic disk, and an optical disk drive that reads from or writes to a removable, nonvolatile optical disk such as a CD ROM, DVD, and Blu-Ray® disk, or other optical media. Computer-readable storage mediamay include, but is not limited to, Zip® drives, flash memory cards, universal serial bus (USB) flash drives, secure digital (SD) cards, DVD disks, digital video tape, and the like. Computer-readable storage mediamay also include, solid-state drives (SSD) based on non-volatile memory such as flash-memory based SSDs, enterprise flash drives, solid state ROM, and the like, SSDs based on volatile memory such as solid state RAM, dynamic RAM, static RAM, DRAM-based SSDs, magnetoresistive RAM (MRAM) SSDs, and hybrid SSDs that use a combination of DRAM and flash memory based SSDs. The disk drives and their associated computer-readable media may provide non-volatile storage of computer-readable instructions, data structures, program modules, and other data for computer system.

2024 2024 2000 2024 2000 2024 2024 Communications subsystemprovides an interface to other computer systems and networks. Communications subsystemserves as an interface for receiving data from and transmitting data to other systems from computer system. For example, communications subsystemmay enable computer systemto connect to one or more devices via the Internet. In some embodiments communications subsystemcan include radio frequency (RF) transceiver components for accessing wireless voice and/or data networks (e.g., using cellular telephone technology, advanced data network technology, such as 3G, 4G or EDGE (enhanced data rates for global evolution), Wi-Fi (IEEE 802.11 family standards, or other mobile communication technologies, or any combination thereof), global positioning system (GPS) receiver components, and/or other components. In some embodiments communications subsystemcan provide wired network connectivity (e.g., Ethernet) in addition to or instead of a wireless interface.

2024 2026 2028 2030 2000 In some embodiments, communications subsystemmay also receive input communication in the form of structured and/or unstructured data feeds, event streams, event updates, and the like on behalf of one or more users who may use computer system.

2024 2026 By way of example, communications subsystemmay be configured to receive data feedsin real-time from users of social networks and/or other communication services such as Twitter® feeds, Facebook® updates, web feeds such as Rich Site Summary (RSS) feeds, and/or real-time updates from one or more third party information sources.

2024 2028 2030 Additionally, communications subsystemmay also be configured to receive data in the form of continuous data streams, which may include event streamsof real-time events and/or event updatesthat may be continuous or unbounded in nature with no explicit end. Examples of applications that generate continuous data may include, for example, sensor data applications, financial tickers, network performance measuring tools (e.g., network monitoring and traffic management applications), clickstream analysis tools, automobile traffic monitoring, and the like.

2024 2026 2028 2030 2000 Communications subsystemmay also be configured to output the structured and/or unstructured data feeds, event streams, event updates, and the like to one or more databases that may be in communication with one or more streaming data source computers coupled to computer system.

2000 Computer systemcan be one of various types, including a handheld portable device (e.g., an iPhone® cellular phone, an iPad® computing tablet, a PDA), a wearable device (e.g., a Google Glass® head mounted display), a PC, a workstation, a mainframe, a kiosk, a server rack, or any other data processing system.

2000 Due to the ever-changing nature of computers and networks, the description of computer systemdepicted in the figure is intended only as a specific example. Many other configurations having more or fewer components than the system depicted in the figure are possible. For example, customized hardware might also be used and/or particular elements might be implemented in hardware, firmware, software (including applets), or a combination. Further, connection to other computing devices, such as network input/output devices, may be employed. Based on the disclosure and teachings provided herein, a person of ordinary skill in the art will appreciate other ways and/or methods to implement the various embodiments.

Although specific embodiments have been described, various modifications, alterations, alternative constructions, and equivalents are also encompassed within the scope of the disclosure. Embodiments are not restricted to operation within certain specific data processing environments but are free to operate within a plurality of data processing environments. Additionally, although embodiments have been described using a particular series of transactions and steps, it should be apparent to those skilled in the art that the scope of the present disclosure is not limited to the described series of transactions and steps. Various features and aspects of the above-described embodiments may be used individually or jointly.

Further, while embodiments have been described using a particular combination of hardware and software, it should be recognized that other combinations of hardware and software are also within the scope of the present disclosure. Embodiments may be implemented only in hardware, or only in software, or using combinations thereof. The various processes described herein can be implemented on the same processor or different processors in any combination. Accordingly, where components or modules are described as being configured to perform certain operations, such configuration can be accomplished, e.g., by designing electronic circuits to perform the operation, by programming programmable electronic circuits (such as microprocessors) to perform the operation, or any combination thereof. Processes can communicate using a variety of techniques including but not limited to conventional techniques for inter process communication, and different pairs of processes may use different techniques, or the same pair of processes may use different techniques at different times.

The specification and drawings are, accordingly, to be regarded in an illustrative rather than a restrictive sense. It will, however, be evident that additions, subtractions, deletions, and other modifications and changes may be made thereunto without departing from the broader spirit and scope as set forth in the claims. Thus, although specific disclosure embodiments have been described, these are not intended to be limiting. Various modifications and equivalents are within the scope of the following claims.

The use of the terms “a” and “an” and “the” and similar referents in the context of describing the disclosed embodiments (especially in the context of the following claims) are to be construed to cover both the singular and the plural, unless otherwise indicated herein or clearly contradicted by context. The terms “comprising,” “having,” “including,” and “containing” are to be construed as open-ended terms (i.e., meaning “including, but not limited to,”) unless otherwise noted. The term “connected” is to be construed as partly or wholly contained within, attached to, or joined together, even if there is something intervening. Recitation of ranges of values herein are merely intended to serve as a shorthand method of referring individually to each separate value falling within the range, unless otherwise indicated herein and each separate value is incorporated into the specification as if it were individually recited herein. All methods described herein can be performed in any suitable order unless otherwise indicated herein or otherwise clearly contradicted by context. The use of any and all examples, or exemplary language (e.g., “such as”) provided herein, is intended merely to better illuminate embodiments, and does not pose a limitation on the scope of the disclosure unless otherwise claimed. No language in the specification should be construed as indicating any non-claimed element as essential to the practice of the disclosure.

Disjunctive language such as the phrase “at least one of X, Y, or Z,” unless specifically stated otherwise, is intended to be understood within the context as used in general to present that an item, term, etc., may be either X, Y, or Z, or any combination thereof (e.g., X, Y, and/or Z). Thus, such disjunctive language is not generally intended to, and should not, imply that certain embodiments require at least one of X, at least one of Y, or at least one of Z to each be present.

Preferred embodiments of this disclosure are described herein, including the best mode known for carrying out the disclosure. Variations of those preferred embodiments may become apparent to those of ordinary skill in the art upon reading the foregoing description. Those of ordinary skill should be able to employ such variations as appropriate and the disclosure may be practiced otherwise than as specifically described herein. Accordingly, this disclosure includes all modifications and equivalents of the subject matter recited in the claims appended hereto as permitted by applicable law. Moreover, any combination of the above-described elements in all possible variations thereof is encompassed by the disclosure unless otherwise indicated herein.

All references, including publications, patent applications, and patents, cited herein are hereby incorporated by reference to the same extent as if each reference were individually and specifically indicated to be incorporated by reference and were set forth in its entirety herein.

In the foregoing specification, aspects of the disclosure are described with reference to specific embodiments thereof, but those skilled in the art will recognize that the disclosure is not limited thereto. Various features and aspects of the above-described disclosure may be used individually or jointly. Further, embodiments can be utilized in any number of environments and applications beyond those described herein without departing from the broader spirit and scope of the specification. The specification and drawings are, accordingly, to be regarded as illustrative rather than restrictive.